[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

[CVPR 2024] Probing the 3D Awareness of Visual Foundation Models

[ICLR 2024] Github Repo for "HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion"

More relighting!

A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

This repository contains the code for the work ID-to-3D.

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Official Implementation of LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

SAMPart3D: Segment Any Part in 3D Objects