JackZhouSz

Analogist

Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model (SIGGRAPH 2024)

BSDF_diffusion_sampling

[SIGGRAPH Asia 2024] BSDF importance sampling using a diffusion model

cinematic-gaussians

Code for our paper "Application of 3D Gaussian Splatting for Cinematic Anatomy on Consumer Class Devices"

differential_wos

Experimental codebase for Differential Walk on Spheres.

EMOPortraits

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

fast_dipole_sums

Code release for "3D reconstruction with fast dipole sums"

FluxMusic

Text-to-Music Generation with Rectified Flow Transformer

fs-lmv

Reproduction of "Adaptive Recurrent Frame Prediction with Learnable Motion Vectors" [SIGGRAPH Asia 2023].

GarmentCode

A modular programming framework for designing parametric sewing patterns

Hi3D-Official

[MM24] Official codes and datasets for ACM MM24 paper "Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models".

hierarchical-3d-gaussians

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

MambaVision

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

MATTopo

MATTopo: Topology-preserving Medial Axis Transform with Restricted Power Diagram. Conditionally accepted to ACM Transactions on Graphics (SIGGRAPH Asia 2024).

Mesh-processing-library

C++ libraries and programs demonstrating mesh processing research published in ACM SIGGRAPH (1992-2003)

Modal-Folding

Modal Folding: Discovering Smooth Folding Patterns for Sheet Materials using Strain-Space Modes [SIGGRAPH 2024]

neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Open-MAGVIT2

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

PuzzleAvatar

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

RadarFields

Frequency-Space Neural Scene Representations for FMCW Radar

RealisDance

The official implementation of RealisDance

RealisHuman

Code of RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images

ReSTIR-SSS

Source code for the paper "ReSTIR Subsurface Scattering for Real-Time Path Tracing" (HPG 2024)

SdfManipulation

Public page of "Direct Manipulation of Procedural Implicit Surfaces"(Siggraph Asia 2024)

signed-heat-3d

signed-heat-demo

SING

[SIGGRAPH Asia 2024] SING: Stability-Incorporated Neighborhood Graph

StableDelight

StableDelight: Real-Time Reflection Removal from Textured Surfaces

StarDecompositionMaps

vggsfm

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

VHAP

A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.