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.

📢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

43,923 subscribers

29,830 views • 3 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀We are thrilled to release an alpha version of OnePoseViaGen - a system for Panoptic 4D Scene Reconstruction from RGB video! 👉Try it at : #AI #3D #GenerativeAI

🚀We are thrilled to release an alpha version of OnePoseViaGen - a system for Panoptic 4D Scene Reconstruction from RGB video! 👉Try it at : #AI #3D #GenerativeAI

Chongjie Ye

23,158 views • 11 months ago

Excited to share Norman Müller's DiffRF: Rendering-guided 3D Radiance Field Diffusion #CVPR2023 highlight! 2D diffusion is great, but what about 3D? We show radiance field diffusion with rendering guidance for consistent and editable 3D synthesis. Vid:

Excited to share Norman Müller's DiffRF: Rendering-guided 3D Radiance Field Diffusion #CVPR2023 highlight! 2D diffusion is great, but what about 3D? We show radiance field diffusion with rendering guidance for consistent and editable 3D synthesis. Vid:

Matthias Niessner

118,156 views • 3 years ago

🚨 ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning RGB-D images -> 3D scene-graphs -> enhance with vision-language features Enables a wide range of perception and planning abilities. Deployed in many real-world use-cases.

🚨 ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning RGB-D images -> 3D scene-graphs -> enhance with vision-language features Enables a wide range of perception and planning abilities. Deployed in many real-world use-cases.

Krishna Murthy

75,593 views • 2 years ago

Project Light Touch from Adobe enables you to modify the lighting in any image. You can move the lighting anywhere within a scene in 3D space, adjusting its color, position, depth, and brightness.

Project Light Touch from Adobe enables you to modify the lighting in any image. You can move the lighting anywhere within a scene in 3D space, adjusting its color, position, depth, and brightness.

CHRIS FIRST

107,325 views • 8 months ago

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

Matthias Niessner

16,835 views • 1 year ago

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

AK

33,933 views • 2 years ago

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

Matthias Niessner

17,985 views • 1 month ago

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,713 views • 1 year ago

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.

Xiaolong Wang

42,767 views • 2 years ago

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

160,702 views • 3 years ago

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 views • 3 years ago

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”

Rerun

12,865 views • 2 years ago

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2

Gordon Wetzstein

52,480 views • 2 years ago

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 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

69,652 views • 3 years ago

InfiniDepth: Fine-grained depth estimation at any resolution; models depth as a neural implicit field instead of a grid; - tops DepthAnything; - recovers sharp details w/ a lightweight 15M decoder.

InfiniDepth: Fine-grained depth estimation at any resolution; models depth as a neural implicit field instead of a grid; - tops DepthAnything; - recovers sharp details w/ a lightweight 15M decoder.

Wildminder

59,172 views • 6 months ago

At #CVPR2024: Tactile-augmented Radiance Fields! We probe a scene with a touch sensor and localize each sample within a NeRF. We use diffusion to estimate the tactile signals for the points we didn't touch. w/ Yiming Dou, Antonio Loquercio, Fengyu Yang, Yi Liu

At #CVPR2024: Tactile-augmented Radiance Fields! We probe a scene with a touch sensor and localize each sample within a NeRF. We use diffusion to estimate the tactile signals for the points we didn't touch. w/ Yiming Dou, Antonio Loquercio, Fengyu Yang, Yi Liu

Andrew Owens

38,616 views • 2 years ago

📢📢📢 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 🇨🇦

77,827 views • 2 years ago

How do we reconstruct a 3D scene from photos with varying exposures? Standard methods often fail, leaving you with blown-out colors or disturbing shadows. We're excited to introduce Neural Exposure Fields (NExF), our new work accepted at #NeurIPS2025! 🧵

How do we reconstruct a 3D scene from photos with varying exposures? Standard methods often fail, leaving you with blown-out colors or disturbing shadows. We're excited to introduce Neural Exposure Fields (NExF), our new work accepted at #NeurIPS2025! 🧵

Michael Niemeyer

132,003 views • 9 months ago