Ruofan Liang

@yxue_yxue Gamers still constantly claim it is AI slop 😔

Immediately makes HOI-Blender result much more photorealistic lol

I also took a picture of this classic place for the teaser demo of our #CVPR26 paper LuxRemix (luxremix.github.io) 😄 I used to love to sit there on Saturday afternoon, hoping Einstein could give me some research ideas 🤣 Credits also to @c_richardt for composing the vid.

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall. DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality. Learn More → nvidia.com/en-us/geforce/…

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 360anything.github.io 🧵

Excited to share our new work: LuxRemix ✨ We leverage diffusion models to decompose complex light transport into individual sources. You can interactively remix room lighting in 2D images or 3D GSplats 💡🎛️ Try the interactive light controls here: 🔗 luxremix.github.io

Amazing 🤯

🚀Beyond the easy video types we previously used for model training, I also tried a lot of vibe coding to add an experimental support for physics-based object drop simulation. I never get tired of watch such object dropping videos 😆

The generated data can be used for training generative rendering models such as our Diffusion Renderer, UniRelight, and LuxDiT. 🌐 Github Repo: github.com/nexuslrf/compo…

Just dropped a Blender-based data generation tool that can be used to render randomly composed synthetic scenes with all G-Buffer attributes. 😋

@yxue_yxue Cool~

#InfiniHuman: Infinite 3D Human Generation with Precise Control How do you want to generate a 3D avatar? From text description? With clothing images? Or some desired body shape? All can be done at once with InfiniHuman! 🔗Page: yuxuan-xue.com/infini-human/ #SIGGRAPHAsia2025 #AI

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: research.nvidia.com/labs/toronto-a… Arxiv: arxiv.org/abs/2510.04290 Code and model are coming.

📢 SceneComp @ ICCV 2025 🏝️ 🌎 Generative Scene Completion for Immersive Worlds 🛠️ Reconstruct what you know AND 🪄 Generate what you don’t! 🙌 Meet our speakers @angelaqdai, @holynski_, @jampani_varun, @ZGojcic @taiyasaki, Peter Kontschieder scenecomp.github.io #ICCV2025

This work is done during my internship at @NVIDIAAI , with other amazing collaborators @Kai__He @ZGojcic @igilitschenski @FidlerSanja @nanditav17† @zianwang97† 🌐 Project page: research.nvidia.com/labs/toronto-a…

LuxDiT, like our earlier works #DiffusionRenderer and #UniRelight, is another exploration into using generative models for inverse rendering, enabling high-quality lighting estimation from casually captured footage.

💡 Introducing LuxDiT: a diffusion transformer (DiT) that estimates realistic scene lighting from a single image or video. It produces accurate HDR environment maps, addressing a long-standing challenge in computer vision. 🔗Paper: arxiv.org/abs/2509.03680

Amazing 🤩

@rishit_dagli Sigh 😔

thanks, very useful review