Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

[SIGGRAPH '25] EVA: Expressive Virtual Avatars from Multi-view Videos Contributions: 1. We introduce EVA, a novel method enabling full-body control with real-time, photo-realistic renderings, robustly handling loose clothing dynamics and various facial expressions. 2. We develop an expressive deformable template that generates a deformable human template mesh and employs... show more

MrNeRF

16,912 subscribers

18,502 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Comments

MrNeRF1 year ago

Paper: Project:

Page to Pixel Publishing2 years ago

The Art of Flight is a homage to 80s/90s arcade action shmups with a fresh twist on the genre. Pilot multiple ships at the same time to take on oncoming waves of enemies in this fast paced space shooter. Wishlist on Steam today!

revolver ocelot1 year ago

It's good but yet to see it in practical or implemented

MrNeRF1 year ago

I'm crafting an email newsletter that turns my daily updates into a captivating weekly digest, complete with exclusive content. Although it's not live yet, you can sign up now! If you're curious, visit my website and join the subscriber list today!

Marc Habermann1 year ago

We will soon release source code and data :) concerning skeleton and mesh: our representation comes with both.

MrNeRF1 year ago

Author's thread:

темпдельтавелю1 year ago

Looks like this impossible to control . How difficult will be to convert to mesh + pose skeleton ?

Rajendra Singh1 year ago

Wow, this is phenomenal

Bobby Rajesh Malhotra ⁴⁴⁴1 year ago

A real eye opener

Related Videos

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

MrNeRF

27,354 views • 2 years ago

URAvatar: Universal Relightable Gaussian Codec Avatars Contributions (cited): (1) We introduce a universal relightable avatar prior model learned from hundreds of dynamic performance captures with a multi-view and multi-light system. (2) We build a drivable head avatar from a phone scan that can be rendered and relit with global light transport in real-time. (3) A capture system and evaluation protocol to measure the accuracy of relighting under continuous illuminations.

MrNeRF

50,123 views • 2 years ago

(1/2) Excited to share "Learning Neural Parametric Head Models" #CVPR2023! We capture over 5200 high-quality 3D human head scans from which we build a neural parametric head model that disentangles & expressions and deformations.

(1/2) Excited to share "Learning Neural Parametric Head Models" #CVPR2023! We capture over 5200 high-quality 3D human head scans from which we build a neural parametric head model that disentangles & expressions and deformations.

Matthias Niessner

53,332 views • 3 years ago

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

Matthias Niessner

69,702 views • 3 years ago

Media2Face Co-speech Facial Animation Generation With Multi-Modality Guidance project page: The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of lexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality expressions and accurate head poses from a large array of videos. This presents the M2F-D dataset, a large, diverse, and scan-level co-speech 3D facial animation dataset with well-annotated emotional and style labels. Finally, we propose Media2Face, a diffusion model in GNPFA latent space for co-speech facial animation generation, accepting rich multi-modality guidances from audio, text, and image. Extensive experiments demonstrate that our model not only achieves high fidelity in facial animation synthesis but also broadens the scope of expressiveness and style adaptability in 3D facial animation.

Media2Face Co-speech Facial Animation Generation With Multi-Modality Guidance project page: The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of lexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality expressions and accurate head poses from a large array of videos. This presents the M2F-D dataset, a large, diverse, and scan-level co-speech 3D facial animation dataset with well-annotated emotional and style labels. Finally, we propose Media2Face, a diffusion model in GNPFA latent space for co-speech facial animation generation, accepting rich multi-modality guidances from audio, text, and image. Extensive experiments demonstrate that our model not only achieves high fidelity in facial animation synthesis but also broadens the scope of expressiveness and style adaptability in 3D facial animation.

AK

79,484 views • 2 years ago

[SIGGRAPH Asia '24 (TOG)] Representing Long Volumetric Video with Temporal Gaussian Hierarchy Contributions: • We introduce a novel, efficient, and expressive Temporal Gaussian Hierarchy representation for long volumetric video. To our knowledge, our method is the first approach capable of handling minutes of volumetric video data. • We propose a Compact Appearance Model and a new rasterization implementation to facilitate real-time, high-quality dynamic view synthesis while maintaining a compact size. • We propose a system to efficiently model long volumetric videos for the first time and demonstrate state-of-the-art dynamic view synthesis quality on the Neural3DV [Li et al. 2022], ENeRF-Outdoor [Lin et al. 2022], and MobileStage [Xu et al. 2024b] datasets, while also achieving the best rendering speed with reduced training cost and memory usage.

[SIGGRAPH Asia '24 (TOG)] Representing Long Volumetric Video with Temporal Gaussian Hierarchy Contributions: • We introduce a novel, efficient, and expressive Temporal Gaussian Hierarchy representation for long volumetric video. To our knowledge, our method is the first approach capable of handling minutes of volumetric video data. • We propose a Compact Appearance Model and a new rasterization implementation to facilitate real-time, high-quality dynamic view synthesis while maintaining a compact size. • We propose a system to efficiently model long volumetric videos for the first time and demonstrate state-of-the-art dynamic view synthesis quality on the Neural3DV [Li et al. 2022], ENeRF-Outdoor [Lin et al. 2022], and MobileStage [Xu et al. 2024b] datasets, while also achieving the best rendering speed with reduced training cost and memory usage.

MrNeRF

79,493 views • 1 year ago

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.

AK

327,442 views • 3 years ago

ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based local expression features and increase the representation capacity by synthesizing 3D Gaussians dynamically by leveraging tiny scaffold MLPs conditioned on localized expressions. We further propose a color-based densification and progressive training scheme for improved quality and faster convergence. Project: Video: Great work by Shivangi, Sebastian Weiss, Irene Baeza, Prashanth Chandran, Gaspard Zoss, Derek Bradley

ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based local expression features and increase the representation capacity by synthesizing 3D Gaussians dynamically by leveraging tiny scaffold MLPs conditioned on localized expressions. We further propose a color-based densification and progressive training scheme for improved quality and faster convergence. Project: Video: Great work by Shivangi, Sebastian Weiss, Irene Baeza, Prashanth Chandran, Gaspard Zoss, Derek Bradley

Matthias Niessner

17,318 views • 1 year ago

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 views • 10 months ago

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

MrNeRF

53,292 views • 1 year ago

Relightable Full-Body Gaussian Codec Avatars TL;DR: First drivable full-body avatar model that reconstructs perceptually realistic relightable appearance. Contributions: • We propose the first relightable full-body avatar model that jointly models the relightable appearance of the human body, face, and hands for high-fidelity relighting and animation. • To handle full-body articulations with global light transport, we propose learnable zonal harmonics to represent local diffuse radiance transfer in the local coordinate frames of each Gaussian. This results in a reduced number of parameters and improved rendering quality compared to the commonly used spherical harmonics representation. • We reformulate the learnable radiance transfer to explicitly decompose non-local shadowing and propose a dedicated shadow network to predict shadows caused by the articulation of the body. Additionally, we propose a physically based irradiance normalization scheme to ensure that the shadow network can generalize to novel illumination conditions, such as unseen environment maps. • We show that deferred shading can be used for our learned specular radiance transfer function, achieving high-fidelity specular reflections for relightable human avatar modeling without excessively increasing the number of Gaussians.

MrNeRF

11,094 views • 1 year ago

SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes abs: paper page: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes abs: paper page: Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find non-trivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

AK

76,380 views • 3 years ago

[SIGGRAPH '25] TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling Note: On the left that's a 3DGS rendering! Contributions: 1. We propose a simple approach for rigging 3D Gaussians within the continuous tangent space of 3DMM face models, allowing Gaussians to move freely across mesh triangles. 2. We propose a novel CNN-based deformation model that is agnostic to the number of 3D Gaussians, naturally enabling adaptively densification of the representation to improve detail where most needed, with expression-dependent shading. 3. We show significant improvements over baseline SOTA methods and demonstrate the ability to render even extreme close-up images at high quality.

[SIGGRAPH '25] TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling Note: On the left that's a 3DGS rendering! Contributions: 1. We propose a simple approach for rigging 3D Gaussians within the continuous tangent space of 3DMM face models, allowing Gaussians to move freely across mesh triangles. 2. We propose a novel CNN-based deformation model that is agnostic to the number of 3D Gaussians, naturally enabling adaptively densification of the representation to improve detail where most needed, with expression-dependent shading. 3. We show significant improvements over baseline SOTA methods and demonstrate the ability to render even extreme close-up images at high quality.

MrNeRF

29,057 views • 1 year ago

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

AK

141,058 views • 2 years ago

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

MrNeRF

25,893 views • 1 year ago

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 views • 3 years ago

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.

MrNeRF

23,814 views • 1 year ago