Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of 1920×1080.

/pdf/instant-neural-graphics-primitives-with-a-multiresolution-g4qducu3.pdf

Instant neural graphics primitives with a multiresolution hash encoding

We propose a technique for fusing a bracketed exposure sequence into a high quality image, without converting to High dynamic range (HDR) first. Skipping the physically based HDR assembly step simplifies the acquisition pipeline. This avoids camera response curve calibration and is computationally efficient. It also allows for including flash images in the sequence. Our technique blends multiple exposures, guided by simple quality measures like saturation and contrast. This is done in a multiresolution fashion to account for the brightness variation in the sequence. The resulting image quality is comparable to existing tone mapping operators.

Exposure Fusion: A Simple and Practical Alternative to High Dynamic Range Photography

Tone-mapping operators (TMOs) that convert high dynamic range (HDR) to low dynamic range (LDR) images provide practically useful tools for the visualization of HDR images on standard LDR displays. Different TMOs create different tone-mapped images, and a natural question is which one has the best quality. Without an appropriate quality measure, different TMOs cannot be compared, and further improvement is directionless. Subjective rating may be a reliable evaluation method, but it is expensive and time consuming, and more importantly, is difficult to be embedded into optimization frameworks. Here we propose an objective quality assessment algorithm for tone-mapped images by combining: 1) a multiscale signal fidelity measure on the basis of a modified structural similarity index and 2) a naturalness measure on the basis of intensity statistics of natural images. Validations using independent subject-rated image databases show good correlations between subjective ranking score and the proposed tone-mapped image quality index (TMQI). Furthermore, we demonstrate the extended applications of TMQI using two examples - parameter tuning for TMOs and adaptive fusion of multiple tone-mapped images.

/pdf/objective-quality-assessment-of-tone-mapped-images-3q1qnzs1dr.pdf

Objective Quality Assessment of Tone-Mapped Images

We present an image-based modeling and editing system that takes a single photo as input. We represent a scene as a layered collection of depth images, where each pixel encodes both color and depth. Starting from an input image, we employ a suite of user-assisted techniques, based on a painting metaphor, to assign depths and extract layers. We introduce two specific editing operations. The first, a “clone brushing tool,” permits the distortion-free copying of parts of a picture, by using a parameterization optimization technique. The second, a “texture-illuminance decoupling filter,” discounts the effect of illumination on uniformly textured areas, by decoupling large- and small-scale features via bilateral filtering. Our system enables editing from different viewpoints, extracting and grouping of image-based objects, and modifying the shape, color, and illumination of these objects.

/pdf/image-based-modeling-and-photo-editing-2ye7pvltxg.pdf

Image-based modeling and photo editing

We propose a technique for fusing a bracketed exposure sequence into a high quality image, without converting to HDR first. Skipping the physically-based HDR assembly step simplifies the acquisition pipeline. This avoids camera response curve calibration and is computationally efficient. It also allows for including flash images in the sequence. Our technique blends multiple exposures, guided by simple quality measures like saturation and contrast. This is done in a multiresolution fashion to account for the brightness variation in the sequence. The resulting image quality is comparable to existing tone mapping operators.

Exposure Fusion

We propose a fast, high quality tone mapping technique to display high contrast images on devices with limited dynamic range of luminance values. The method is based on logarithmic compression of luminance values, imitating the human response to light. A bias power function is introduced to adaptively vary logarithmic bases, resulting in good preservation of details and contrast. To improve contrast in dark areas, changes to the gamma correction procedure are proposed. Our adaptive logarithmic mapping technique is capable of producing perceptually tuned images with high dynamic content and works at interactive speed. We demonstrate a successful application of our tone mapping technique with a high dynamic range video player enabling to adjust optimal viewing conditions for any kind of display while taking into account user preference concerning brightness, contrast compression, and detail reproduction.

/pdf/adaptive-logarithmic-mapping-for-displaying-high-contrast-1bph2oxtis.pdf

Adaptive Logarithmic Mapping For Displaying High Contrast Scenes

We present Convolution Shadow Maps, a novel shadow representation that affords efficient arbitrary linear filtering of shadows. Traditional shadow mapping is inherently non-linear w.r.t. the stored depth values, due to the binary shadow test. We linearize the problem by approximating shadow test as a weighted summation of basis terms. We demonstrate the usefulness of this representation, and show that hardware-accelerated anti-aliasing techniques, such as tri-linear filtering, can be applied naturally to Convolution Shadow Maps. Our approach can be implemented very efficiently in current generation graphics hardware, and offers real-time frame rates.

Convolution shadow maps

Shadow computation in dynamic scenes under complex illumination is a challenging problem. Methods based on precomputation provide accurate, real-time solutions, but are hard to extend to dynamic scenes. Specialized approaches for soft shadows can deal with dynamic objects but are not fast enough to handle more than one light source. In this paper, we present a technique for rendering dynamic objects under arbitrary environment illumination, which does not require any precomputation. The key ingredient is a fast, approximate technique for computing soft shadows, which achieves several hundred frames per second for a single light source. This allows for approximating environment illumination with a sparse collection of area light sources and yields real-time frame rates.

/pdf/real-time-all-frequency-shadows-in-dynamic-scenes-fp38et42lq.pdf

Real-time, all-frequency shadows in dynamic scenes

Rendering high-quality shadows in real-time is a challenging problem. Shadow mapping has proved to be an efficient solution, as it scales well for complex scenes. However, it suffers from aliasing problems. Filtering the shadow map alleviates aliasing, but unfortunately, native hardware-accelerated filtering cannot be applied, as the shadow test has to take place beforehand.

We introduce a simple approach to shadow map filtering, by approximating the shadow test using an exponential function. This enables us to pre-filter the shadow map, which in turn allows for high quality hardware-accelerated filtering. Compared to previous filtering techniques, our technique is faster, consumes less memory and produces less artifacts.

Exponential shadow maps

In this paper we present a shadow mapping technique for hemispherical and omnidirectional light sources using dual-paraboloid mapping. In contrast to the traditional perspective projection this parameterization has the benefit that only a minimal number of rendering passes is needed during generation of the shadow maps, making the method suitable for dynamic environments and real time applications. By utilizing programmable features available on state-of-the-art graphics cards we show how the algorithm can be efficiently mapped to hardware.

Thomas Annen

Papers

Adaptive Logarithmic Mapping For Displaying High Contrast Scenes

Convolution shadow maps

Real-time, all-frequency shadows in dynamic scenes

Exponential shadow maps

Shadow Mapping for Hemispherical and Omnidirectional Light Sources