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.
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.
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.
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.
Check out extra video results including uncompressed videos and some reference videos.
Dynamic demonstrations of RenderFormer's capabilities, showing object rotations, lighting changes, and material adjustments.
RenderFormer can render animations of scenes.
RenderFormer can render physically simulated scenes with complex dynamics and interactions.
@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}
}