LumiX: Structured and Coherent Text-to-Intrinsic Generation
This addresses the challenge of coherent text-to-intrinsic generation for computer vision and graphics applications, representing a novel method for a known bottleneck.
The paper tackles the problem of generating multiple intrinsic maps (e.g., albedo, depth) from text prompts by proposing LumiX, a structured diffusion framework that ensures physical consistency, resulting in 23% higher alignment and improved preference scores compared to state-of-the-art methods.
We present LumiX, a structured diffusion framework for coherent text-to-intrinsic generation. Conditioned on text prompts, LumiX jointly generates a comprehensive set of intrinsic maps (e.g., albedo, irradiance, normal, depth, and final color), providing a structured and physically consistent description of an underlying scene. This is enabled by two key contributions: 1) Query-Broadcast Attention, a mechanism that ensures structural consistency by sharing queries across all maps in each self-attention block. 2) Tensor LoRA, a tensor-based adaptation that parameter-efficiently models cross-map relations for efficient joint training. Together, these designs enable stable joint diffusion training and unified generation of multiple intrinsic properties. Experiments show that LumiX produces coherent and physically meaningful results, achieving 23% higher alignment and a better preference score (0.19 vs. -0.41) compared to the state of the art, and it can also perform image-conditioned intrinsic decomposition within the same framework.