We present ReSTIR Path Guiding (ReSTIR-PG), a real-time method that extracts guiding distributions from resampled paths produced by ReSTIR and uses them to generate improved initial candidates for the next frame. While ReSTIR significantly reduces variance through spatiotemporal resampling, its effectiveness is ultimately limited by the quality of the initial candidates, which are often poorly distributed and introduce correlation artifacts. Our key observation is that ReSTIR’s accepted paths already approximate the target path contribution density, and that their bounce directions follow the ideal distribution for local path guiding – the product of incident radiance and the cosine-weighted BSDF. We exploit this structure to fit lightweight guiding distributions using each frame’s resampled paths by density estimation. Compared to conventional guiding based on raw path-traced samples, ReSTIR-PG closes the loop between guiding and resampling. Our method achieves lower variance, faster response time to scene change, reduced correlation artifacts, all while preserving real-time performance.

Recovering high-fidelity spatially varying bidirectional reflectance distribution function (SVBRDF) maps from a single image remains an ill-posed and challenging problem, especially in the presence of saturated highlights. Existing methods often fail to reconstruct the underlying texture in regions overwhelmed by intense specular reflections. This kind of bake-in artifacts caused by highlight corruption can be greatly alleviated by providing a series of material images under different lighting conditions. To this end, our key insight is to leverage the strong priors of diffusion models to generate images of the same material under varying lighting conditions. These generated images are then used to aid a multi-image SVBRDF estimator in recovering highlight-free reflectance maps. However, strong highlights in the input image lead to inconsistencies across the relighting results. Moreover, texture reconstruction becomes unstable in saturated regions, with variations in background structure, specular shape, and overall material color. These artifacts degrade the quality of SVBRDF recovery. To address this issue, we propose a shuffle-based background consistency module that extracts stable background features and implicitly identifies saturated regions. This guides the diffusion model to generate coherent content while preserving material structures and details. Furthermore, to stabilize the appearance of generated highlights, we introduce a lightweight specular prior encoder that estimates highlight features and then performs grid-based latent feature translation, injecting consistent specular contour priors while preserving material color fidelity. Both quantitative analysis and qualitative visualization demonstrate that our method enables stable neural relighting from a single image and can be seamlessly integrated into multi-input SVBRDF networks to estimate highlight-free reflectance maps.

Abstract We propose a new image‐based representation for real‐time distant objects rendering: Reshadable Impostors with Level‐of‐Detail (RiLoD). By storing compact geometric and material information captured from a few reference views, RiLoD enables reliable forward mapping to generate target views under dynamic lighting and edited material attributes. In addition, it supports seamless transitions across different levels of detail. To support reshading and LoD simultaneously while maintaining a minimal memory footprint and bandwidth requirement, our key design is a compact yet efficient representation that encodes and compresses the necessary material and geometric information in each reference view. To further improve the visual fidelity, we use a reliable forward mapping technique combined with a hole‐filling filtering strategy to ensure geometric completeness and shading consistency. We demonstrate the practicality of RiLoD by integrating it into a modern real‐time renderer. RiLoD delivers fast performance across a variety of test scenes, supports smooth transitions between levels of detail as the camera moves closer or farther, and avoids the typical artifacts of impostor techniques that result from neglecting the underlying geometry.

We introduce ExtraSS, a novel framework that combines spatial super sampling and frame extrapolation to enhance real-time rendering performance. By integrating these techniques, our approach achieves a balance between performance and quality, generating temporally stable and high-quality, high-resolution results. Leveraging lightweight modules on warping and the ExtraSSNet for refinement, we exploit spatial-temporal information, improve rendering sharpness, handle moving shadings accurately, and generate temporally stable results. Computational costs are significantly reduced compared to traditional rendering methods, enabling higher frame rates and alias-free high resolution results. Evaluation using Unreal Engine demonstrates the benefits of our framework over conventional individual spatial or temporal super sampling methods, delivering improved rendering speed and visual quality. With its ability to generate temporally stable high-quality results, our framework creates new possibilities for real-time rendering applications, advancing the boundaries of performance and photo-realistic rendering in various domains.

Abstract We present a new software ray tracing solution that efficiently computes visibilities in dynamic scenes. We first introduce a novel scene representation: ray‐aligned occupancy map array (ROMA) that is generated by rasterizing the dynamic scene once per frame. Our key contribution is a fast and low‐divergence tracing method computing visibilities in constant time, without constructing and traversing the traditional intersection acceleration data structures such as BVH. To further improve accuracy and alleviate aliasing, we use a spatiotemporal scheme to stochastically distribute the candidate ray samples. We demonstrate the practicality of our method by integrating it into a modern real‐time renderer and showing better performance compared to existing techniques based on distance fields (DFs). Our method is free of the typical artifacts caused by incomplete scene information, and is about 2.5×–10× faster than generating and tracing DFs at the same resolution and equal storage.

Basis functions provide both the abilities for compact representation and the properties for efficient computation. Therefore, they are pervasively used in rendering to perform all-frequency shading. However, common basis functions, including spherical harmonics (SH), wavelets, and spherical Gaussians (SG) all have their own limitations, such as low-frequency for SH, not rotationally invariant for wavelets, and no multiple product support for SG. In this paper, we present neural basis functions, an implicit and data-driven set of basis functions that circumvents the limitations with all desired properties. We first introduce a representation neural network that takes any general 2D spherical function (e.g. environment lighting, BRDF, and visibility) as input and projects it onto the latent space as coefficients of our neural basis functions. Then, we design several lightweight neural networks that perform different types of computation, giving our basis functions different computational properties such as double/triple product integrals and rotations. We demonstrate the practicality of our neural basis functions by integrating them into all-frequency shading applications, showing that our method not only achieves a compression rate of and 10 × -40 × better performance than wavelets at equal quality, but also renders all-frequency lighting effects in real-time without the aforementioned limitations from classic basis functions.

Abstract Real‐time ray tracing (RTRT) is being pervasively applied. The key to RTRT is a reliable denoising scheme that reconstructs clean images from significantly undersampled noisy inputs, usually at 1 sample per pixel as limited by current hardware's computing power. The state of the art reconstruction methods all rely on temporal filtering to find correspondences of current pixels in the previous frame, described using per‐pixel screen‐space motion vectors. While these approaches are demonstrated powerful, they suffer from a common issue that the temporal information cannot be used when the motion vectors are not valid, i.e. when temporal correspondences are not obviously available or do not exist in theory. We introduce temporally reliable motion vectors that aim at deeper exploration of temporal coherence, especially for the generally‐believed difficult applications on shadows, glossy reflections and occlusions, with the key idea to detect and track the cause of each effect. We show that our temporally reliable motion vectors produce significantly better temporal results on a variety of dynamic scenes when compared to the state of the art methods, but with negligible performance overhead.