258 citations · 310 across the 18 of their papers we have counts for
19 papers
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
Xiaoyang Liu, Shangzhe Wu, Kai Han
3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-…
Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control
Ruining Li, Yuxin Yao, Matt Zhou +5
Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations. Recent neural networks can estimate the articulated structure of 3D objects, but…
Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
Matt Zhou, Ruining Li, Xiaoyang Lyu +6
A bottleneck in learning to understand articulated 3D objects is the lack of large and diverse datasets. In this paper, we propose to leverage large language models (LLMs) to close…
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
Anbang Wang, Yuzhuo Ao, Shangzhe Wu +1
Native 3D generative models have achieved remarkable fidelity and speed, yet they suffer from a critical limitation: inability to prescribe precise structural articulations, where…
Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow
Shenhan Qian, Ganlin Zhang, Shangzhe Wu +1
Reconstructing and tracking dynamic 3D scenes is a fundamental challenge in computer vision. Existing methods typically decouple geometry from motion: static multi-view reconstruct…
Particulate: Feed-Forward 3D Object Articulation
Ruining Li, Yuxin Yao, Chuanxia Zheng +4
We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion const…
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
Ben Kaye, Tomas Jakab, Shangzhe Wu +2
The choice of data representation is a key factor in the success of deep learning in geometric tasks. For instance, DUSt3R recently introduced the concept of viewpoint-invariant po…
Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
Tomas Jakab, Ruining Li, Shangzhe Wu +2
We present Farm3D, a method for learning category-specific 3D reconstructors for articulated objects, relying solely on "free" virtual supervision from a pre-trained 2D diffusion-b…
ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
Shengnan Liang, Yichen Liu, Shangzhe Wu +2
We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3…
CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Keqiang Sun, Shangzhe Wu, Ning Zhang +3
Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of con…
MagicPony: Learning Articulated 3D Animals in the Wild
Shangzhe Wu, Ruining Li, Tomas Jakab +2
We consider the problem of predicting the 3D shape, articulation, viewpoint, texture, and lighting of an articulated animal like a horse given a single test image as input. We pres…
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Keqiang Sun, Shangzhe Wu, Zhaoyang Huang +3
Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of con…
De-rendering 3D Objects in the Wild
Felix Wimbauer, Shangzhe Wu, Christian Rupprecht
With increasing focus on augmented and virtual reality applications (XR) comes the demand for algorithms that can lift objects from images and videos into representations that are…
NeRF--: Neural Radiance Fields Without Known Camera Parameters
Zirui Wang, Shangzhe Wu, Weidi Xie +2
Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by rem…
Self-Supervised Localisation between Range Sensors and Overhead Imagery
Tim Y. Tang, Daniele De Martini, Shangzhe Wu +1
Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are n…
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each inpu…
Photo-Geometric Autoencoding to Learn 3D Objects from Unlabelled Images
Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
We show that generative models can be used to capture visual geometry constraints statistically. We use this fact to infer the 3D shape of object categories from raw single-view im…
Image Generation from Sketch Constraint Using Contextual GAN
Yongyi Lu, Shangzhe Wu, Yu-Wing Tai +1
In this paper we investigate image generation guided by hand sketch. When the input sketch is badly drawn, the output of common image-to-image translation follows the input edges d…
Deep High Dynamic Range Imaging with Large Foreground Motions
Shangzhe Wu, Jiarui Xu, Yu-Wing Tai +1
This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR…