Inspired by generative paradigms in image and video, 3D shape generation has made notable progress, enabling the rapid synthesis of high-fidelity 3D assets from a single image. However, current methods still face challenges, including the lack of intricate details, overly smoothed surfaces, and fragmented thin-shell structures. These limitations leave the generated 3D assets still one step short of meeting the standards favored by artists. In this paper, we present ShapeGen, which achieves high-quality image-to-3D shape generation through 3D representation and supervision improvements, resolution scaling up, and the advantages of linear transformers. These advancements allow the generated assets to be seamlessly integrated into 3D pipelines, facilitating their widespread adoption across various applications. Specifically, in contrast to existing methods: 1) We investigate how different representations and VAE supervision strategies affect the generation process, and address issues like aliasing artifacts and fragmented thin-shell structures by using an TSDF-based representation supervised with BCE loss. 2) We scale up the resolution of 3D data, image conditioning inputs, and the number of latent tokens to enhance generation fidelity. 3) We adopt mixed conditioning using raw RGB images and normal maps during training, effectively resolving ambiguities caused by inconsistencies between ControlNet-generated RGB images and the underlying geometry from untextured assets. 4) We replace the original softmax attention with linear attention to improve training and inference efficiency when handling a large number of latent tokens. 5) We introduce an inference-time scaling strategy that enhances generation quality at test time. Through extensive experiments, we validate the impact of these improvements on overall performance. Ultimately, thanks to the synergistic effects of these enhancements, ShapeGen achieves a significant leap in image-to-3D generation, establishing a new state-of-the-art performance.

In this work we consider control problems for discrete-time dynamical systems with safety constraints. As opposed to the existing work on similar problems, we assume that the system at run-time can preview some of the future uncontrolled inputs (e.g., disturbances). In order to develop a control synthesis technique that can leverage such preview information, we introduce a mathematical construct called Preview Automaton that incorporates system dynamics with the prior knowledge on the structure of the preview. We propose an algorithm to find the maximum controlled invariant set for the Preview Automaton. Although Preview Automaton can be equivalently represented by a Finite Transition System, for which existing control synthesis methods can be applied, we show that exploiting the structure of the Preview Automaton results in more efficient solution algorithms. These ideas are demonstrated with a lane-keeping problem, where we show that existence of the preview information allows the vehicle to safely navigate roads with larger curvature, whereas the problem becomes infeasible when no preview information is available.

Finding small objects is fundamentally challenging because there is little signal on the object to exploit. For the small-scale pedestrian detection, one must use image evidence beyond the pedestrian extent, which is often formulated as context. Unlike existing object detection methods that use adjacent regions or whole image as the context simply, we focus on more informed contexts exploiting and utilizing to improve small-scale pedestrian detection: firstly, one relationship network is developed to utilize the correlation among pedestrian instances in one image; secondly, two spatial regions, overhead area and feet bottom area, are taken as spatial context to exploit the relevance between pedestrian and scenes; at last, GRU [7] (Gated Recurrent Units) modules are introduced to take encoded contexts as input to guide the feature selection and fusion of each proposal. Instead of getting all of the outputs at once, we also iterate twice to refine the detection incrementally. Comprehensive experiments on Caltech Pedestrian [8] and SJTU-SPID [9] datasets, indicate that, with more informed context, the detection performance can be improved significantly, especially for the small-scale pedestrians.