正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

(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

49,098 subscribers

69,702 次观看 • 3 年前 •via X (Twitter)

教育科学技术新闻政治 #SIGGRAPH

Anya Rossi• Live Now

Private livecam show

3 条评论

Matthias Niessner 的头像

Matthias Niessner3 年前

(2/2) To train our model, we record a novel multi-view video dataset from 16 cameras containing over 4700 sequences of human heads covering a variety of facial expressions. The dataset will be publicly available to advance research on high-fidelity human head reconstruction.

Tobias Kirschstein 的头像

Tobias Kirschstein3 年前

Super excited to present NeRSemble at #SIGGRAPH2023 in the NeRFs for Avatars session happening tomorrow (Thursday) 3:45pm in Petree Hall C! Come by to chat about human-centric dynamic radiance fields and other face-related 3D topics!

Bobcat 的头像

Bobcat3 年前

That is just insane. You'll be outperforming ground truth in no time

相关视频

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 次观看 • 3 年前

We released our ActorsHQ dataset from our #SIGGRAPH work: "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion". ActorsHQ provides high-fidelity multi-view captures at 12MP resolution from 160 cameras with per-frame mesh reconstructions.

We released our ActorsHQ dataset from our #SIGGRAPH work: "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion". ActorsHQ provides high-fidelity multi-view captures at 12MP resolution from 160 cameras with per-frame mesh reconstructions.

Matthias Niessner

22,748 次观看 • 3 年前

[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 a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.

[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 a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.

MrNeRF

18,502 次观看 • 1 年前

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

AK

20,668 次观看 • 2 年前

New Video! Excited to share our work on fast view synthesis of casual videos. 🤩 high-quality dynamic view synthesis 🤩 applicable for a wide range of casual videos 🤩 fast training and rendering

New Video! Excited to share our work on fast view synthesis of casual videos. 🤩 high-quality dynamic view synthesis 🤩 applicable for a wide range of casual videos 🤩 fast training and rendering

Jia-Bin Huang

27,360 次观看 • 2 年前

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

Siyuan Huang

12,833 次观看 • 1 年前

[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 次观看 • 1 年前

[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 次观看 • 1 年前

(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 次观看 • 3 年前

(1/2) 📢📢𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬 📢📢 High-fidelity 3D head avatars with precise control over viewpoint, expression, and pose. -> Our parametric 3D model enables control & consistency + 2D diffusion makes it photoreal.

(1/2) 📢📢𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧𝐀𝐯𝐚𝐭𝐚𝐫𝐬 📢📢 High-fidelity 3D head avatars with precise control over viewpoint, expression, and pose. -> Our parametric 3D model enables control & consistency + 2D diffusion makes it photoreal.

Matthias Niessner

66,436 次观看 • 2 年前

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

AK

160,723 次观看 • 3 年前

📢📢📢 Excited to share our new work *Autonomous Character-Scene Interaction Synthesis from Text Instruction* (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

📢📢📢 Excited to share our new work Autonomous Character-Scene Interaction Synthesis from Text Instruction (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

Siyuan Huang

11,451 次观看 • 2 年前

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

Matthias Niessner

29,937 次观看 • 3 年前

[SIGGRAPH ASIA '25] Detail-Enhanced Gaussian Splatting for Large-Scale Volumetric Capture Contributions: - A two-stage approach to performance capture, combining a scene-scale capture rig and a single-actor facial capture rig. - A novel high-quality scene-scale volumetric performance capture rig, incorporating both static and dynamic cameras to track the performance of multiple actors. - A reconstruction pipeline for dynamic performance capture, featuring stable calibration of moving cameras and 4DGS with improved dynamic range and color fidelity. - A detail enhancement Diffusion Model, which supports 4K, RGB, and Alpha, with improved temporal stability.

[SIGGRAPH ASIA '25] Detail-Enhanced Gaussian Splatting for Large-Scale Volumetric Capture Contributions: - A two-stage approach to performance capture, combining a scene-scale capture rig and a single-actor facial capture rig. - A novel high-quality scene-scale volumetric performance capture rig, incorporating both static and dynamic cameras to track the performance of multiple actors. - A reconstruction pipeline for dynamic performance capture, featuring stable calibration of moving cameras and 4DGS with improved dynamic range and color fidelity. - A detail enhancement Diffusion Model, which supports 4K, RGB, and Alpha, with improved temporal stability.

MrNeRF

42,570 次观看 • 11 个月前

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 次观看 • 3 年前

📢📢📢 Introducing "𝐁𝐚𝐲𝐞𝐬' 𝐑𝐚𝐲𝐬: Uncertainty Quantification for Neural Radiance Fields" TL;DR: 𝐜𝐚𝐧 𝐈 "𝐭𝐫𝐮𝐬𝐭" 𝐦𝐲 𝐍𝐞𝐑𝐅 𝐚𝐭 𝐩𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐱? with Lily Goli , @sellan_s, Cody Reading, Alec Jacobson.

📢📢📢 Introducing "𝐁𝐚𝐲𝐞𝐬' 𝐑𝐚𝐲𝐬: Uncertainty Quantification for Neural Radiance Fields" TL;DR: 𝐜𝐚𝐧 𝐈 "𝐭𝐫𝐮𝐬𝐭" 𝐦𝐲 𝐍𝐞𝐑𝐅 𝐚𝐭 𝐩𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐱? with Lily Goli , @sellan_s, Cody Reading, Alec Jacobson.

Andrea Tagliasacchi

77,876 次观看 • 3 年前

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!

Matthias Niessner

11,425 次观看 • 1 年前

📢📢📢Data release: high-res, multi-view, OLAT face recordings 📢📢📢 We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain

📢📢📢Data release: high-res, multi-view, OLAT face recordings 📢📢📢 We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain

Matthias Niessner

19,536 次观看 • 9 个月前

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

Matthias Niessner

22,703 次观看 • 1 年前

GaussianSpeech: Audio-Driven Gaussian Avatars Contributions: • The first transformer-based sequence model for audio-driven head animation synthesis of a lightweight 3DGS based avatar. By animating our optimized 3DGS avatar directly with our transformer model, we achieve temporally coherent animation sequences while characterizing fine-scale face details and speaker-specific style. • A new high-quality audio-video dataset, comprising high-resolution 16-view dataset of 6 native English speakers (Standard American & British). The dataset has a total of 2500 sequences, with overall recordings of ∼3.5 hours.

MrNeRF

11,477 次观看 • 1 年前