Pontus Ebelin
@_pandersson
Followers
77
Following
788
Media
0
Statuses
97
Our upcoming HPG 2025 paper ”Collaborative Texture Filtering” is up! Research done with @_pandersson, Matt Pharr, and @BartWronsk. https://t.co/ZZtPU8vkJB
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...
1
30
79
I'm excited to share our latest paper (work with Matt Pharr and @inversepixel ), "Improved Stochastic Texture Filtering Through Sample Reuse" accepted to I3D'2025. https://t.co/8N9dlSdplT
https://t.co/WTtpMHfHlW 1/
3
53
209
The 2nd workshop on Computer Vision for Videogames will be organized at CVPR 2025: this is a great venue for gaming-related research (think AI, genAI, graphics, RL, agents, HCI — with applications to videogames). There is still time to submit: https://t.co/DFlU1Qgn8v
#CVPR2025
0
4
19
We are hiring a Ph.D. intern (in-person at an NVIDIA, USA, office; California preferred) to work on multi-modal foundation models + agents / digital avatars. Ideal candidate is one with a track record of leading impactful research & the ability to obtain work permit in the US.
1
29
245
The #HPG2024 student competition is live! If you're a student interested in computer graphics, we encourage you to participate and remix some classic computer graphics images! https://t.co/R6w7uJljFy (credits: neural bunny by blackle, AsciiArt Teapot by Sebastien Durand-2014)
0
7
45
- 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 https://t.co/a5nWWuF2ua. 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
Over the summer this project will likely focus on the generative AI side and need that skill set. Excited to work with @ekta_prashnani on this! Contact us if you’re interested.
We are hiring a Ph.D. Intern @ NVIDIA, to work on generative models, visual perception, and quality of digital avatars. Ideal candidate is someone with a track record of leading impactful work. Contact @RuthRosenholtz or me if you think you would be a good fit. Details in thread.
1
3
12
We are hiring a Ph.D. Intern @ NVIDIA, to work on generative models, visual perception, and quality of digital avatars. Ideal candidate is someone with a track record of leading impactful work. Contact @RuthRosenholtz or me if you think you would be a good fit. Details in thread.
1
13
133
It should now be easier than ever to use ꟻLIP.
Single header FLIP.h, for both CPU-only and CUDA, has just been released: https://t.co/upem5dZD5m
0
0
5
EGSR 2024 will be at Imperial College, London, on July 3rd through 5th. See https://t.co/5ZnIQfV8uD. The Call for Papers is now up, and Ruth Rosenholtz (from MIT and NVIDIA) has accepted our invitation for the first keynote. Hope to see you there!
0
16
34
Thrilled to announce our work "Conditional Resampled Importance Sampling and ReSTIR" (SIGGRAPH Asia 2023). We extend RIS and ReSTIR into conditional probability spaces, enabling novel forms of sample reuse. 1/7
2
83
307
New #NVIDIAResearch paper: SLANG.D: Fast, Modular and Differentiable Shader Programming: shows how a single language serves as a unified platform for real-time, inverse, and differentiable rendering. Collaboration with @MIT, @UCSanDiego, & @UW. 🧵 1/2 https://t.co/5DHzQldMMV
1
40
171
Clarifying an earlier call: We are looking for a Ph.D. intern @ NVIDIA for research on human perception of 3D scenes. Human vision and/or graphics background with an interest in human vision. DM me if interested or have questions. Please spread the word.
2
17
50
We are hiring a Ph.D. intern @ NVIDIA for research on multi-modal generative models, reinforcement learning, self-supervised representations, and 3D perception for video conferencing. If you have experience leading insightful contributions on any of these topics, DM / email me.
3
57
272
We finally get to share our neural materials research. We created custom highly-realistic reference materials, we invented new neural models, and we built new graphics systems. End result is these neural materials run in a real-time path tracer. https://t.co/EOHnRbjjS1
8
108
456
NVIDIA is thrilled to share our SIGGRAPH 2023 papers. It is our best SIGGRAPH yet, with ~20 papers authored in partnership with over a dozen universities. Generative AI, 3D content creation, neural rendering, neural physics, and more... https://t.co/fN6f3g2eDQ
3
71
249