The paper introduces a real‑time technique for reconstructing fully integrated pixel radiance in volumetric media under both direct and ambient illumination. It bypasses expensive path‑traced radiance estimates by inferring the final light‑transport solution from compact scene features and statistics, using an attention‑augmented image‑to‑image network. The method achieves high reconstruction accuracy in challenging volumetric cloud scenarios while maintaining stable computational cost regardless of camera zoom or volume density.
arXiv:2606.26738v3 Announce Type: replace Abstract: While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these syst...
arXiv:2609.28300v1 Announce Type: new Abstract: Ill-posed inverse problems require priors to constrain the solution space toward plausible outcomes. In inverse rendering, learned priors modeling the...
PureLight introduces a neural approach to estimate the appearance of complex luminaires that are difficult for traditional path tracing, such as small emitters surrounded by multiple specular layers. The method uses light tracing to build paths from emitters to exit surfaces and learns the probability density function of outgoing radiance with a large normalizing flow network, then distills this into a lightweight MLP for efficient inference. Additionally, a sampling network and a blending network are trained to compute direct illumination and composite the luminaire into arbitrary scenes, enabling low‑sample rendering of challenging luminaires.
arXiv:2610.32075v1 Announce Type: new Abstract: Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing. Existing tra...
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their versatility and integration with conventional graphics workflows. We introduce Floating Radiance Networks (FlaRe), a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions.
arXiv:2512.23667v3 Announce Type: replace Abstract: Intrinsic image decomposition aims to recover material and illumination factors from RGB observations, but real-world images entangle reflectance w...
JointLight introduces an asynchronous joint-modeling approach for human-centric video relighting, enabling fine-grained illumination control by jointly denoising RGB and irradiance frames during two-stage training. The method employs a domain matching strategy to bridge gaps between synthetic irradiance cues and real irradiance maps, and uses an asynchronous hijacked generation pipeline at inference. A newly created multi-illumination synthetic video dataset with paired irradiance maps supports training, and the model demonstrates strong generalization to real-world scenarios, outperforming prior methods in lighting fidelity and generative quality.
Recent advances in Intrinsic Image Decomposition (IID) have increasingly relied on generative models. However, progress remains limited by three key challenges: (a) insufficient physical consistency,...
arXiv:2606. 30380v1 Announce Type: cross Abstract: We present RenderFormer++, a scalable and physically grounded feed-forward neural rendering framework for global illumination in mesh scenes.
GLOW is a Global Illumination‑aware inverse rendering framework for indoor scenes captured with dynamic co‑located light and camera setups. It combines a neural implicit surface representation with a neural radiance cache to jointly optimize geometry and reflectance, while introducing a dynamic radiance cache and a surface‑angle‑weighted radiometric loss to handle near‑field motion, strong inter‑reflections, and specular highlights. Experiments demonstrate that GLOW significantly outperforms prior methods in estimating material reflectance under both natural and co‑located illumination.
GS-PI introduces an optimization‑decoupled framework that transforms Gaussian Splatting (GS) assets into physically based rendering (PBR) compatible Gaussian assets. By treating PBR material generation as a geometry‑conditioned diffusion process on 3D point clouds, it achieves multi‑view consistency and avoids the pixel‑correspondence problems of 2D diffusion. The method employs a multi‑scale cross‑view conditioning mechanism—combining global semantic priors, photometric cues, and spatial view‑direction signals—to prevent specular highlights from baking into intrinsic colors, and then distills the predicted attributes back into a fully relightable PBR‑GS asset without requiring proxy meshes.
RawSLAM introduces the first online Gaussian SLAM framework that operates directly on single‑exposure 16‑bit linear HDR images, overcoming the limitations of traditional 8‑bit LDR SLAM systems in extreme lighting. The approach combines an HDR Gaussian splatting module with a Reinhard‑compressed photometric objective and structure‑guided spatial weighting, achieving superior trajectory and reconstruction accuracy compared to a direct HDR adaptation of MonoGS. The same formulation also improves performance on standard 8‑bit inputs and can be transferred to other SLAM systems such as SplaTAM, Gaussian SLAM, and DROID‑W, eliminating tracking failures in challenging illumination sequences. Additionally, RawSLAM provides a new dataset of 10 real‑world indoor sequences with 16‑bit RAW imagery, depth, IMU, and OptiTrack poses.