We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes, each corresponding to a semantically meaningful part. The 3D scene information is encoded in one single triplane tensor, from which multiple Signed Distance Function (SDF) fields can be decoded to represent the compositional shapes. During training, an auto-encoder compresses tri-planes into a latent space, and then the denoising diffusion process is employed to approximate the distribution of the compositional scenes. Frankenstein demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts. The generated scenes facilitate many downstream applications, such as part-wise re-texturing, object rearrangement in the room or avatar cloth re-targeting.

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

In this paper, we propose a method to design generalized frequency response masking (FRM)-based P-L band multi-channel channelizers for array signal processing system (ASPS), which have sharp transition bandwidth (STB) and low complexity. The order of the prototype filter with STB designed by FRM method is smaller than that of the direct filter design method. The design approach of the proposed generalized FRM-based multi-channel channelizers is presented which solves the problem of high computational complexity of digital channelizer with STB. The proposed generalized FRM-based digital channelizer, which have the characteristics of unification and flexible configuration, is suitable for real signal, complex signal, odd-stacked, even-stacked, maximally decimation and non-maximally decimation structures. The generalized FRM-based P-L band multi-channel channelizers for ASPS is implemented in a Xilinx Kintex UltraScale XCKU115 processor. Experimental results show that the proposed generalized FRM-based digital channelizer offers 84.57% and 76.24% reduction in multipliers complexity and chip power respectively, which is less than conventional polyphase digital channelizer (PDC).