No, you really do need to just linearize it :) Even if you are linearizing with the generic default gamma, it should go a long way.
14.10.2025 18:00 — 👍 1 🔁 0 💬 0 📌 0
Interesting point.
The same problem with living in the sRGB space also applies to Gaussian filtering (or really any linear operation). Before you simply blur your image, or resample/resize etc., it is theoretically necessary to first linearize the image.
14.10.2025 04:12 — 👍 1 🔁 0 💬 1 📌 0
Research Themes
Research Themes
Find our work on inverse rendering and illumination-aware computational photography in our group web page: yaksoy.github.io/themes/
04.08.2025 08:38 — 👍 1 🔁 0 💬 0 📌 0
SFU Researchers Develop A New Tool That Brings Blender-like Lighting Control to Any Photograph
Users can interactively insert different light sources including spot lights, point lights, projectors, or environmental illumination with full 3D control.
Read our press release: www.sfu.ca/fas/computin...
04.08.2025 08:38 — 👍 1 🔁 0 💬 1 📌 0
YouTube video by Yağız Aksoy - Computational Photography Lab @ SFU
Physically Controllable Relighting of Photographs - SIGGRAPH 2025
In this work led by Chris Careaga, we combine physically-based rendering, differentiable rendering, and neural rendering to achieve realistic relighting in any photograph in-the-wild.
Watch Chris' fancy video explainer: youtu.be/XFJCT3D8t0M
04.08.2025 08:38 — 👍 1 🔁 0 💬 1 📌 0
We are bringing Blender-like explicit control over light sources to photo relighting in our new SIGGRAPH paper! 📸
🧵
04.08.2025 08:38 — 👍 17 🔁 1 💬 1 📌 0
Avid reader, computer graphics fan and atmospheric jungle beats enjoyer. Demoscene: cce/Peisik.
Blog at https://30fps.net/
cpu, gpu @sketchfab @fab @epicgames
Computer graphics from c64 to ungodly number of shader processor on modern 3d rigs
Only cpu/gpu/dev/gamdev/vfx content
Graphics researcher at TU Delft. Formerly Intel, KIT, NVIDIA, Uni Bonn. Known for moment shadow maps, MBOIT, blue noise, spectra, light sampling. Opinions are my own.
https://MomentsInGraphics.de
Associate Professor at UMD CS. YouTube: https://youtube.com/@jbhuang0604
Interested in how computers can learn and see.
Assist. Prof - Mid Sweden University
Immersive imaging technologies, QoE, data visualization, AR/VR
We make heaps of gaming stuff :D
https://linktr.ee/vldl
🇵🇭 Support me on Patreon!
https://www.patreon.com/JamesRehwald
Film Camera Enthusiast. Former Director of Engineering at Napster (formerly The Infinite Reality.) Currently interested in Vulkan, WebGPU, parametric geometry. Github.com/danielbelmes
Professor at ETH Zürich, Research Scientist at Google
Professor of Robotics, University of Zurich
Professor of Computer Vision and AI at TU Munich, Director of the Munich Center for Machine Learning mcml.ai and of ELLIS Munich ellismunich.ai
cvg.cit.tum.de
Researcher at Google, 3D computer vision & machine learning. Previously PhD at ETH Zurich, intern at Google, Meta Reality Labs, Microsoft, MagicLeap. Migrating from x.com/pesarlin ...
Computing Science prof in multimodal embodied AI, emotion, interaction at SFU in Vancouver 🇨🇦🇵🇭 Director of the Rosie Lab www.rosielab.ca Robotics nerd. Previously at SoftBank Robotics 🤖 FR/JP
sebastian-dille.github.io
Assistant Professor of Computer Science at TU Darmstadt, Member of @ellis.eu, DFG #EmmyNoether Fellow, PhD @ETH
Computer Vision & Deep Learning
Computer Graphics & Vision @ Adobe
From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.
Computational Photography Researcher @ Adobe, previously Princeton PhD: https://ilyac.info
I sometimes do a regular photography: http://instagram.com/_ilya_c
Our lab: https://light.princeton.edu/
Prof ETH Zürich, Director Microsoft Spatial AI Lab, CV/ML/Robotics
