Peter Wonka

PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation

LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning

Generative Human Geometry Distribution

ShapeGen4D: Towards High Quality 4D Shape Generation from Videos

T-3DGS: Removing Transient Objects for 3D Scene Reconstruction

iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation

StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart

PDTrack: Progressive Dense 3D Tracking

FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

PFGS: Pose-Fused 3D Gaussian Splatting for Complete Multi-Pose Object Reconstruction

BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models?

Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation

LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion

Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

A3D: Does Diffusion Dream about 3D Alignment?

Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation

VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR Data

Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models

PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models

VIA: Unified Spatiotemporal Video Adaptation for Global and Local Video Editing

ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning