Ayan Kumar Bhunia's repositories
Sketch2Saliency
[CVPR-23] Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings, EEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2023.
Awesome-Diffusion-Personalization
A collection of resources on personalization with diffusion models.
plug-and-play
Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)
w-plus-adapter
w-plus-adapter
3Doodle
Official implementation of 3Doodle: Compact Abstraction of Objects with 3D Strokes (SIGGRAPH 24')
AToM
Official implementation of `AToM: Amortized Text-to-Mesh using 2D Diffusion`
AyanKumarBhunia.github.io
https://ayankumarbhunia.github.io/
coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Diffusion-3D-Features
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features [CVPR 2024]
EpiDiff
[CVPR 2024] EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
GeoAware-SC
Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"
img2img-turbo
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
ml-cvnets
CVNets: A library for training computer vision networks
multidiffusion-upscaler-for-automatic1111
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Neural-Radiance-Caching
Sandbox for graphics paper implementation
NRC-HPM-Renderer
Bachelor Thesis: Real-time Neural Radiance Caching in Heterogeneous Participating Media
ReSTIR_DR
Source Code for SIGGRAPH 2023 Paper "Parameter-space ReSTIR for Differentiable and Inverse Rendering"
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
SLiMe
1-shot image segmentation using Stable Diffusion
SwiftFormer
[ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Torch-Pruning
[CVPR-2023] Towards Any Structural Pruning; LLaMA / YOLOv8 / CNNs / Transformers
Upscale-A-Video
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
VisDiff
Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)