Abstract We propose a novel ray reordering technique designed to accelerate the ray tracing process by encoding and sorting rays prior to traversal. Our method, called “hierarchy cut code”, involves encoding rays based on the cuts of the hierarchical acceleration structure, rather than relying solely on spatial coordinates. This approach allows for a more effective adaptation to the acceleration structure, resulting in a more reliable and efficient encoding outcome. Furthermore, our research identifies “bounding drift” as a major obstacle in achieving better acceleration effects using longer sorting keys in existing reordering methods. Fortunately, our hierarchy cut code successfully overcomes this issue, providing improved performance in ray tracing. Experimental results demonstrate the effectiveness of our approach, showing up to a 1.81 times faster secondary ray tracing compared to existing methods. These promising results highlight the potential for further enhancement in the acceleration effect of reordering techniques, warranting further exploration and research in this exciting field.

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners: by pre-training on unconditional image generation, DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders, thus making diffusion pre-training emerge as a general approach for generative-and-discriminative dual learning. To validate this, we conduct linear probe and finetuning evaluations. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet, respectively, and is comparable to contrastive learning and masked autoencoders for the first time. Transfer learning from ImageNet also confirms the suitability of DDAE for Vision Transformers, suggesting the potential to scale DDAEs as unified foundation models. Code is available at github.com/FutureXiang/ddae.

This paper investigates a new fine-grained video generation task, namely Multi-view Gait Video Synthesis, where the generation model works on a video of a walking human of arbitrary viewpoint and creates multi-view renderings of the subject. This task is particularly challenging, as it requires synthesizing visually plausible results, while simultaneously preserving discriminative gait cues subject to identification. To tackle the challenge caused by the entanglement of viewpoint, texture, and body structure, we present a network with two collaborative branches to decouple the novel view rendering process into two streams for human appearances (texture) and silhouettes (structure), respectively. Additionally, the prior knowledge of person re-identification and gait recognition is incorporated into the training loss for more adequate and accurate dynamic details. Experimental results show that the presented method is able to achieve promising success rates when attacking state-of-the-art gait recognition models. Furthermore, the method can improve gait recognition systems by effective data augmentation. To the best of our knowledge, this is the first task to manipulate views for human videos with person-specific behavioral constraints.

This article investigates the joint effects of connection weight and time delay on pattern formation for a delayed reaction-diffusion BAM neural network (RDBAMNN) with Neumann boundary conditions by using the$({k_{1}},{k_{2}})$mode Hopf-zero bifurcation. First, the conditions for${k_{1}}$mode zero bifurcation are obtained by choosing connection weight as the bifurcation parameter. It is found that the connection weight has a great impact on the properties of steady state. With connection weight increasing, the homogeneous steady state becomes inhomogeneous, which means that the connection weight can affect the spatial stability of steady state. Then, the specified conditions for the${k_{2}}$mode Hopf bifurcation and the$({k_{1}},{k_{2}})$mode Hopf-zero bifurcation are established. By using the center manifold, the third-order normal form of the Hopf-zero bifurcation is obtained. Through the analysis of the normal form, the bifurcation diagrams on two parameters’ planes (connection weight and time delay) are obtained, which contains six areas. Some interesting spatial patterns are found in these areas: a homogeneous periodic solution, a homogeneous steady state, two inhomogeneous steady state, and two inhomogeneous periodic solutions.

Training a deep generative adversarial network (GAN) with hundreds or even thousands of layers is difficult. The backpropagation depth of generator is deeper than discriminator, leading it to occur vanishing/exploding gradients easily. This paper proposes a method to train deep vanilla GAN based on mean field theory. By adjusting the parameter variances and activation of the GAN, a 200-layer vanilla GAN can be trained steadily without adding any batch normalization layers or residual blocks. We demonstrate that deep GAN is very sensitive to the parameter variances $\sigma _w^2$ , $\sigma _b^2$ in the initialization scheme, and explain why hard tanh is more suitable than relu as an activation in a deep vanilla GAN. Experiments on the MNIST and Fashion-MNIST data sets validate that our method trains a deep vanilla GAN well and can produce high-quality images.