Tianyuan Zhang

9

Papers

303

Total Citations

Papers (9)

Physics-Based Interaction with 3D Objects via Video Generation

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors

Embracing Single Stride 3D Object Detector With Sparse Transformer

Analyzing Physical Impacts Using Transient Surface Wave Imaging

ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries

Real-Time Intermediate Flow Estimation for Video Frame Interpolation