https://microsoft.github.io/renderformer/ RF IntroductionGalleryVideosBibTeX More Research NRHintsDiLightNetGS^3 RenderFormer Transformer-based Neural Rendering of Triangle Meshes with Global Illumination SIGGRAPH 2025 Chong Zeng^1,2Yue Dong^2Pieter Peers^3Hongzhi Wu^1Xin Tong^2 ^1State Key Lab of CAD and CG, Zhejiang University ^2Microsoft Research Asia ^3College of William & Mary arXiv Paper Code Model RenderFormer results Introduction We present RenderFormer, a neural rendering pipeline that directly renders an image from a triangle-based representation of a scene with full global illumination effects and that does not require per-scene training or fine-tuning. Mesh to Image, End to End Instead of taking a physics-centric approach to rendering, we formulate rendering as a sequence-to-sequence transformation where a sequence of tokens representing triangles with reflectance properties is converted to a sequence of output tokens representing small patches of pixels. Simple Transformer Architecture with Minimal Prior Constraints RenderFormer follows a two stage pipeline: a view-independent stage that models triangle-to-triangle light transport, and a view-dependent stage that transforms a token representing a bundle of rays to the corresponding pixel values guided by the triangle-sequence from the the view-independent stage. Both stages are based on the transformer architecture and are learned with minimal prior constraints. No rasterization, no ray tracing. Model architecture Rendering Gallery Examples of scenes rendered with RenderFormer demonstrating various lighting conditions, materials, and geometric complexity, without any per-scene training or fine-tuning. Check out the reference images for more details. Cornell Box Cornell Box Source: Cornell University Program of Computer Graphics Cornell Box with Bunny Stanford Bunny in Cornell Box Source: Stanford University Computer Graphics Laboratory Cornell Box with Lucy Lucy Statue Source: Stanford University Computer Graphics Laboratory Cornell Box with Teapot Utah Teapot Source: University of Utah, Utah Model Repository Composed Scene Composed Scene Source: Fausto Javier Da Rosa and Keenan Crane Constant Width Scene Constant Width Bodies Source: Keenan Crane Crystal Scene Crystals Source: Mongze Fox Scene Fox in the Wild Source: Vlad Zaichyk Horse and Heart Horse and Heart Source: Microsoft RenderFormer Logo RenderFormer Logo Room Scene Interior Room Source: Microsoft Shader Ball Shader Ball Source: Wenzel Jakob Tree Scene Tree Source: elbenZ Veach MIS Scene Veach MIS Source: Eric Veach Videos Check out extra video results including uncompressed videos and some reference videos. Teaser Scenes Dynamic demonstrations of RenderFormer's capabilities, showing object rotations, lighting changes, and material adjustments. Cornell Box Roughness Adjustment Bunny Roughness Adjustment Tree Light Change Tree Object Rotation Fancy Scene Rotation Composed Scene View Change Animations RenderFormer can render animations of scenes. Cascade Cube Animation Source: Tycho Magnetic Anomaly Animated Crab Source: Bohdan Lvov Gyroscope Motion Source: reddification Animated Character Source: mortaleiros Marching Cubes Animation Source: Tycho Magnetic Anomaly Robot Animation Source: Gouhadouken Physical-Based Simulations RenderFormer can render physically simulated scenes with complex dynamics and interactions. Bowling Ball Physics Simulation Source: SINOFWRATH Rotating Box Dynamics Constant Width Body Simulation BibTeX @inproceedings {zeng2025renderformer, title = {RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination}, author = {Chong Zeng and Yue Dong and Pieter Peers and Hongzhi Wu and Xin Tong}, booktitle = {ACM SIGGRAPH 2025 Conference Papers}, year = {2025} } Copy Privacy & CookiesConsumer Health PrivacyTerms of UseTrademarks (c) 2025 Microsoft