52 citations · 70 across the 17 of their papers we have counts for
17 papers
Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction
Jen-Hao Cheng, Yipeng Wang, Hao Zhang +2
We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos usi…
World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible
Hao Zhang, Mohamed El Banani, Jen-Hao Cheng +6
Image-to-3D methods often trade off faithfulness and completeness: depth estimators are anchored to input pixels but stop at the visible surface, while image-to-3D models generate…
PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos
Ting-Hsuan Liao, Haowen Liu, Yiran Xu +3
We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences…
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Ruihan Gao, Kangle Deng, Gengshan Yang +2
3D generation methods have shown visually compelling results powered by diffusion image priors. However, they often fail to produce realistic geometric details, resulting in overly…
Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
Gengshan Yang, Andrea Bajcsy, Shunsuke Saito +1
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on…
DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Jeff Tan, Donglai Xiang, Shubham Tulsiani +2
We present a method to reconstruct time-consistent human body models from monocular videos, focusing on extremely loose clothing or handheld object interactions. Prior work in huma…
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
Nikhil Keetha, Jay Karhade, Krishna Murthy Jatavallabhula +4
Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented reality applications. However, current methods are often hampered by the non-volumetric or…
Reconstructing Animatable Categories from Videos
Gengshan Yang, Chaoyang Wang, N Dinesh Reddy +1
Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories. Recentl…
SLoMo: A General System for Legged Robot Motion Imitation from Casual Videos
John Z. Zhang, Shuo Yang, Gengshan Yang +3
We present SLoMo: a first-of-its-kind framework for transferring skilled motions from casually captured "in the wild" video footage of humans and animals to legged robots. SLoMo wo…
Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis
Chonghyuk Song, Gengshan Yang, Kangle Deng +2
We explore the task of embodied view synthesis from monocular videos of deformable scenes. Given a minute-long RGBD video of people interacting with their pets, we render the scene…
3D-aware Conditional Image Synthesis
Kangle Deng, Gengshan Yang, Deva Ramanan +1
We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model l…
BANMo: Building Animatable 3D Neural Models from Many Casual Videos
Gengshan Yang, Minh Vo, Natalia Neverova +3
Prior work for articulated 3D shape reconstruction often relies on specialized sensors (e.g., synchronized multi-camera systems), or pre-built 3D deformable models (e.g., SMAL or S…
NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild
Jason Y. Zhang, Gengshan Yang, Shubham Tulsiani +1
Recent history has seen a tremendous growth of work exploring implicit representations of geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works are f…
LASR: Learning Articulated Shape Reconstruction from a Monocular Video
Gengshan Yang, Deqing Sun, Varun Jampani +6
Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structur…
Learning to Segment Rigid Motions from Two Frames
Gengshan Yang, Deva Ramanan
Appearance-based detectors achieve remarkable performance on common scenes, but tend to fail for scenarios lack of training data. Geometric motion segmentation algorithms, however,…
Hierarchical Deep Stereo Matching on High-resolution Images
Gengshan Yang, Joshua Manela, Michael Happold +1
We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-art (SOTA) methods struggle to process high-res imagery because of memory constraints or…
Inferring Distributions Over Depth from a Single Image
Gengshan Yang, Peiyun Hu, Deva Ramanan
When building a geometric scene understanding system for autonomous vehicles, it is crucial to know when the system might fail. Most contemporary approaches cast the problem as dep…