Pontus Ebelin
@_pandersson
Followers
77
Following
784
Media
0
Statuses
97
RT @inversepixel: Our upcoming HPG 2025 paper ”Collaborative Texture Filtering” is up!.Research done with .@_pandersson, Matt Pharr, and @B….
research.nvidia.com
Recent advances in texture compression provide major improvements in compression ratios, but cannot use the GPU's texture units for decompression and filtering. This has led to the development of...
0
30
0
RT @BartWronsk: I'm excited to share our latest paper (work with Matt Pharr and @inversepixel ), "Improved Stochastic Texture Filtering Thr….
0
53
0
RT @ekta_prashnani: The 2nd workshop on Computer Vision for Videogames will be organized at CVPR 2025: this is a great venue for gaming-rel….
0
4
0
RT @ekta_prashnani: We are hiring a Ph.D. intern (in-person at an NVIDIA, USA, office; California preferred) to work on multi-modal foundat….
0
29
0
RT @killerooo: The #HPG2024 student competition is live! If you're a student interested in computer graphics, we encourage you to participa….
0
7
0
- Performance improvements for the C++ and CUDA implementations of HDR-FLIP (2x faster HDR-FLIP on CUDA).- . and more!. Implemented in collaboration with @inversepixel. We hope you'll enjoy v1.4! Let us know if you run into any issues.
0
0
0
The update includes . - Install using pip install . - Run FLIP in your own Python evaluation pipeline with import flip and flip.evaluate(. ).- Python implementation now leverages the C++ code through pybind11.
1
0
1
FLIP v1.4 is out! It makes the Python implementation about 20-47x faster than before, and significantly more convenient to use. Code available at Details in 🧵.
1
4
16
- Performance improvements for the C++ and CUDA implementations of HDR-ꟻLIP (2x faster HDR-ꟻLIP on CUDA).- . and more!. Implemented in collaboration with @inversepixel. We hope you'll enjoy v1.4! Let us know if you run into any issues.
0
0
0
The update includes . - Install using pip install . - Run ꟻLIP in your own Python evaluation pipeline with import flip and flip.evaluate(. ).- Python implementation now leverages the C++ code through pybind11.
1
0
0
RT @RuthRosenholtz: Over the summer this project will likely focus on the generative AI side and need that skill set. Excited to work with….
0
3
0
RT @ekta_prashnani: We are hiring a Ph.D. Intern @ NVIDIA, to work on generative models, visual perception, and quality of digital avatars.….
0
13
0
It should now be easier than ever to use ꟻLIP.
Single header FLIP.h, for both CPU-only and CUDA, has just been released:.
0
0
5
RT @EGSympRendering: EGSR 2024 will be at Imperial College, London, on July 3rd through 5th. See The Call for Pape….
0
16
0
RT @nmkettunen: Thrilled to announce our work "Conditional Resampled Importance Sampling and ReSTIR" (SIGGRAPH Asia 2023). We extend RIS an….
0
84
0
RT @NVIDIAAIDev: New #NVIDIAResearch paper: SLANG.D: Fast, Modular and Differentiable Shader Programming: shows how a single language serve….
0
42
0
RT @RuthRosenholtz: Clarifying an earlier call: .We are looking for a Ph.D. intern @ NVIDIA for research on human perception of 3D scenes.….
0
17
0
RT @ekta_prashnani: We are hiring a Ph.D. intern @ NVIDIA for research on multi-modal generative models, reinforcement learning, self-super….
0
59
0
RT @aaronlefohn: We finally get to share our neural materials research. We created custom highly-realistic reference materials, we invente….
0
109
0
RT @aaronlefohn: NVIDIA is thrilled to share our SIGGRAPH 2023 papers. It is our best SIGGRAPH yet, with ~20 papers authored in partnership….
0
73
0