Infinite Motion: Extended Motion Generation via Long Text Instructions

In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to extended motion generation, effectively bridging the gap between short and long-duration motion synthesis. Our core insight is the strategic extension and reassembly of existing high-quality text-motion datasets, which has led to the creation of a novel benchmark dataset to facilitate the training of models for extended motion sequences. A key innovation of our model is its ability to accept arbitrary lengths of text as input, enabling the generation of motion sequences tailored to specific narratives or scenarios. Furthermore, we incorporate the timestamp design for text which allows precise editing of local segments within the generated sequences, offering unparalleled control and flexibility in motion synthesis. We further demonstrate the versatility and practical utility of "Infinite Motion" through three specific applications: natural language interactive editing, motion sequence editing within long sequences and splicing of independent motion sequences. Each application highlights the adaptability of our approach and broadens the spectrum of possibilities for research and development in motion generation. Through extensive experiments, we demonstrate the superior performance of our model in generating long sequence motions compared to existing methods.Project page: https://shuochengzhai.github.io/Infinite-motion.github.io/

GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting

In this work, we propose a novel clothed human reconstruction method called GaussianBody, based on 3D Gaussian Splatting. Compared with the costly neural radiance based models, 3D Gaussian Splatting has recently demonstrated great performance in terms of training time and rendering quality. However, applying the static 3D Gaussian Splatting model to the dynamic human reconstruction problem is non-trivial due to complicated non-rigid deformations and rich cloth details. To address these challenges, our method considers explicit pose-guided deformation to associate dynamic Gaussians across the canonical space and the observation space, introducing a physically-based prior with regularized transformations helps mitigate ambiguity between the two spaces. During the training process, we further propose a pose refinement strategy to update the pose regression for compensating the inaccurate initial estimation and a split-with-scale mechanism to enhance the density of regressed point clouds. The experiments validate that our method can achieve state-of-the-art photorealistic novel-view rendering results with high-quality details for dynamic clothed human bodies, along with explicit geometry reconstruction.

SonicVisionLM: Playing Sound with Vision Language Models

There has been a growing interest in the task of generating sound for silent videos, primarily because of its practicality in streamlining video post-production. However, existing methods for video-sound generation attempt to directly create sound from visual representations, which can be challenging due to the difficulty of aligning visual representations with audio representations. In this paper, we present SonicVisionLM, a novel framework aimed at generating a wide range of sound effects by leveraging vision language models. Instead of generating audio directly from video, we use the capabilities of powerful vision language models (VLMs). When provided with a silent video, our approach first identifies events within the video using a VLM to suggest possible sounds that match the video content. This shift in approach transforms the challenging task of aligning image and audio into more well-studied sub-problems of aligning image-to-text and text-to-audio through the popular diffusion models. To improve the quality of audio recommendations with LLMs, we have collected an extensive dataset that maps text descriptions to specific sound effects and developed temporally controlled audio adapters. Our approach surpasses current state-of-the-art methods for converting video to audio, resulting in enhanced synchronization with the visuals and improved alignment between audio and video components. Project page: https://yusiissy.github.io/SonicVisionLM.github.io/

Hierarchical Fashion Design with Multi-stage Diffusion Models

Cross-modal fashion synthesis and editing offer intelligent support to fashion designers by enabling the automatic generation and local modification of design drafts.While current diffusion models demonstrate commendable stability and controllability in image synthesis,they still face significant challenges in generating fashion design from abstract design elements and fine-grained editing.Abstract sensory expressions, \eg office, business, and party, form the high-level design concepts, while measurable aspects like sleeve length, collar type, and pant length are considered the low-level attributes of clothing.Controlling and editing fashion images using lengthy text descriptions poses a difficulty.In this paper, we propose HieraFashDiff,a novel fashion design method using the shared multi-stage diffusion model encompassing high-level design concepts and low-level clothing attributes in a hierarchical structure.Specifically, we categorized the input text into different levels and fed them in different time step to the diffusion model according to the criteria of professional clothing designers.HieraFashDiff allows designers to add low-level attributes after high-level prompts for interactive editing incrementally.In addition, we design a differentiable loss function in the sampling process with a mask to keep non-edit areas.Comprehensive experiments performed on our newly conducted Hierarchical fashion dataset,demonstrate that our proposed method outperforms other state-of-the-art competitors.

Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training bias, mainly due to class imbalance and long-tail distributions of the point cloud data. As a result, they lead to a biased prediction for the tail class segmentation. In this paper, we introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively. In particular, we first employ two-round pseudo-label generation to select unlabeled points across head-to-tail classes. We further introduce multi-class imbalanced focus loss to adaptively pay more attention to feature learning across head-to-tail classes. We fix the backbone parameters after feature learning and retrain the classifier using ground-truth points to update its parameters. Extensive experiments demonstrate the effectiveness of our method outperforming previous state-of-the-art methods on both indoor and outdoor 3D point cloud datasets (i.e., S3DIS, ScanNet-V2, Semantic3D, and SemanticKITTI) using 1% and 1pt evaluation.

Streaming Motion Forecasting for Autonomous Driving

Trajectory forecasting is a widely-studied problem for autonomous navigation. However, existing benchmarks evaluate forecasting based on independent snapshots of trajectories, which are not representative of real-world applications that operate on a continuous stream of data. To bridge this gap, we introduce a benchmark that continuously queries future trajectories on streaming data and we refer to it as "streaming forecasting." Our benchmark inherently captures the disappearance and re-appearance of agents, presenting the emergent challenge of forecasting for occluded agents, which is a safety-critical problem yet overlooked by snapshot-based benchmarks. Moreover, forecasting in the context of continuous timestamps naturally asks for temporal coherence between predictions from adjacent timestamps. Based on this benchmark, we further provide solutions and analysis for streaming forecasting. We propose a plug-and-play meta-algorithm called "Predictive Streamer" that can adapt any snapshot-based forecaster into a streaming forecaster. Our algorithm estimates the states of occluded agents by propagating their positions with multi-modal trajectories, and leverages differentiable filters to ensure temporal consistency. Both occlusion reasoning and temporal coherence strategies significantly improve forecasting quality, resulting in 25% smaller endpoint errors for occluded agents and 10-20% smaller fluctuations of trajectories. Our work is intended to generate interest within the community by highlighting the importance of addressing motion forecasting in its intrinsic streaming setting. Code is available at https://github.com/ziqipang/StreamingForecasting.

Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation

Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance the performance of lightweight classification models, its application to structured outputs like object detection and instance segmentation remains a complicated task, due to the variability in outputs and complex internal network modules involved in the distillation process. In this paper, we propose a simple yet surprisingly effective sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student. To distill knowledge from a highly accurate but complex teacher model, we construct a sequence of teachers to help the student gradually adapt. Our progressive strategy can be easily combined with existing detection distillation mechanisms to consistently maximize student performance in various settings. To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students, and unprecedentedly boost the performance of ResNet-50 based RetinaNet from 36.5% to 42.0% AP and Mask R-CNN from 38.2% to 42.5% AP on the MS COCO benchmark.

An Empirical Analysis of Range for 3D Object Detection

LiDAR-based 3D detection plays a vital role in autonomous navigation. Surprisingly, although autonomous vehicles (AVs) must detect both near-field objects (for collision avoidance) and far-field objects (for longer-term planning), contemporary benchmarks focus only on near-field 3D detection. However, AVs must detect far-field objects for safe navigation. In this paper, we present an empirical analysis of far-field 3D detection using the long-range detection dataset Argoverse 2.0 to better understand the problem, and share the following insight: near-field LiDAR measurements are dense and optimally encoded by small voxels, while far-field measurements are sparse and are better encoded with large voxels. We exploit this observation to build a collection of range experts tuned for near-vs-far field detection, and propose simple techniques to efficiently ensemble models for long-range detection that improve efficiency by 33% and boost accuracy by 3.2% CDS.

Multi-Modal Face Stylization with a Generative Prior

In this work, we introduce a new approach for artistic face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality stylized faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi-modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder-decoder architecture. Specifically, we use the mid-resolution and high-resolution layers of StyleGAN as the decoder to generate high-quality faces, while aligning its low-resolution layer with the encoder to extract and preserve input facial details. We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine-tuned with artistic data for stylized face generation. To enable the fine-tuned model to be applied in zero-shot and one-shot stylization tasks, we train an additional mapping network from the large-scale Contrastive-Language-Image-Pre-training (CLIP) space to a latent $w+$ space of fine-tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior face stylization performance in both one-shot and zero-shot stylization tasks, outperforming state-of-the-art methods by a large margin.

Learning to Zoom and Unzoom

Many perception systems in mobile computing, autonomous navigation, and AR/VR face strict compute constraints that are particularly challenging for high-resolution input images. Previous works propose nonuniform downsamplers that "learn to zoom" on salient image regions, reducing compute while retaining task-relevant image information. However, for tasks with spatial labels (such as 2D/3D object detection and semantic segmentation), such distortions may harm performance. In this work (LZU), we "learn to zoom" in on the input image, compute spatial features, and then "unzoom" to revert any deformations. To enable efficient and differentiable unzooming, we approximate the zooming warp with a piecewise bilinear mapping that is invertible. LZU can be applied to any task with 2D spatial input and any model with 2D spatial features, and we demonstrate this versatility by evaluating on a variety of tasks and datasets: object detection on Argoverse-HD, semantic segmentation on Cityscapes, and monocular 3D object detection on nuScenes. Interestingly, we observe boosts in performance even when high-resolution sensor data is unavailable, implying that LZU can be used to "learn to upsample" as well.