9 papers
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Jan-Niklas Dihlmann, Andreas Engelhardt, Simon Donne +2
Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy or avoid. In authoring, this…
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
Ciara Rowles, Reshinth Adithyan, Nikhil Pinnaparaju +2
We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedba…
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
Mark Boss, Vikram Voleti, Simon Donné +1
The key-value (KV) cache dominates memory bandwidth and footprint in long-context autoregressive inference. Recent rotation-preconditioned codecs (TurboQuant, PolarQuant) show that…
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
Jan-Niklas Dihlmann, Mark Boss, Simon Donne +3
Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitation…
SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
Andreas Engelhardt, Mark Boss, Vikram Voleti +3
We present Stable Video Materials 3D (SViM3D), a framework to predict multi-view consistent physically based rendering (PBR) materials, given a single image. Recently, video diffus…
ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction
Mark Boss, Andreas Engelhardt, Simon Donné +1
Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Slic…