Yuxiao Guo

Yu-Qi Yang, Yu-Xiao Guo, Jian-Yu Xiong et al.

The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance. We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset. Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets, but also outperforms state-of-the-art methods on downstream tasks with +2.3 mIoU and +2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation, +1.8 mIoU on ScanNet segmentation (val), +1.9 mAP@0.5 on ScanNet detection, and +8.1 mAP@0.5 on S3DIS detection. A series of extensive ablation studies further validate the scalability, generality, and superior performance enabled by our approach. The code and models are available at https://github.com/microsoft/Swin3D .

Siming Yan, Yuqi Yang, Yuxiao Guo et al.

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

Sicheng Xu, Guojun Chen, Yu-Xiao Guo et al.

We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only generating lip movements that are exquisitely synchronized with the audio, but also producing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512x512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors.

Xin-Yang Zheng, Hao Pan, Yu-Xiao Guo et al.

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D data, the MVD methods first generate multiple views of a 3D object based on an image or text prompt and then reconstruct 3D shapes with multiview 3D reconstruction. However, the sparse views and inconsistent details in the generated images make 3D reconstruction challenging. We present MVD$^2$, an efficient 3D reconstruction method for multiview diffusion (MVD) images. MVD$^2$ aggregates image features into a 3D feature volume by projection and convolution and then decodes volumetric features into a 3D mesh. We train MVD$^2$ with 3D shape collections and MVD images prompted by rendered views of 3D shapes. To address the discrepancy between the generated multiview images and ground-truth views of the 3D shapes, we design a simple-yet-efficient view-dependent training scheme. MVD$^2$ improves the 3D generation quality of MVD and is fast and robust to various MVD methods. After training, it can efficiently decode 3D meshes from multiview images within one second. We train MVD$^2$ with Zero-123++ and ObjectVerse-LVIS 3D dataset and demonstrate its superior performance in generating 3D models from multiview images generated by different MVD methods, using both synthetic and real images as prompts.

Ming-Jia Yang, Yu-Xiao Guo, Yang Liu et al.

Generating realistic, room-level indoor scenes with semantically plausible and detailed appearances from in-the-wild images is crucial for various applications in VR, AR, and robotics. The success of NeRF-based generative methods indicates a promising direction to address this challenge. However, unlike their success at the object level, existing scene-level generative methods require additional information, such as multiple views, depth images, or semantic guidance, rather than relying solely on RGB images. This is because NeRF-based methods necessitate prior knowledge of camera poses, which is challenging to approximate for indoor scenes due to the complexity of defining alignment and the difficulty of globally estimating poses from a single image, given the unseen parts behind the camera. To address this challenge, we redefine global poses within the framework of Local-Pose-Alignment (LPA) -- an anchor-based multi-local-coordinate system that uses a selected number of anchors as the roots of these coordinates. Building on this foundation, we introduce LPA-GAN, a novel NeRF-based generative approach that incorporates specific modifications to estimate the priors of camera poses under LPA. It also co-optimizes the pose predictor and scene generation processes. Our ablation study and comparisons with straightforward extensions of NeRF-based object generative methods demonstrate the effectiveness of our approach. Furthermore, visual comparisons with other techniques reveal that our method achieves superior view-to-view consistency and semantic normality.

Ming-Jia Yang, Yu-Xiao Guo, Bin Zhou et al.

We present a method for creating 3D indoor scenes with a generative model learned from a collection of semantic-segmented depth images captured from different unknown scenes. Given a room with a specified size, our method automatically generates 3D objects in a room from a randomly sampled latent code. Different from existing methods that represent an indoor scene with the type, location, and other properties of objects in the room and learn the scene layout from a collection of complete 3D indoor scenes, our method models each indoor scene as a 3D semantic scene volume and learns a volumetric generative adversarial network (GAN) from a collection of 2.5D partial observations of 3D scenes. To this end, we apply a differentiable projection layer to project the generated 3D semantic scene volumes into semantic-segmented depth images and design a new multiple-view discriminator for learning the complete 3D scene volume from 2.5D semantic-segmented depth images. Compared to existing methods, our method not only efficiently reduces the workload of modeling and acquiring 3D scenes for training, but also produces better object shapes and their detailed layouts in the scene. We evaluate our method with different indoor scene datasets and demonstrate the advantages of our method. We also extend our method for generating 3D indoor scenes from semantic-segmented depth images inferred from RGB images of real scenes.

Dongyu Liu, Weiwei Cui, Kai Jin et al.

Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To accelerate the training process and reduce the number of trials, experts need to understand what has occurred in the training process and why the resulting CNN behaves as such. However, current popular training platforms, such as TensorFlow, only provide very little and general information, such as training/validation errors, which is far from enough to serve this purpose. To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log. Specifically,we combine a hierarchical index mechanism and a set of hierarchical small multiples to help experts explore the entire training log from different levels of detail. We also introduce a novel cube-style visualization to reveal the complex correlations among multiple types of heterogeneous training data including neuron weights, validation images, and training iterations. Three case studies are conducted to demonstrate how DeepTracker provides its users with valuable knowledge in an industry-level CNN training process, namely in our case, training ResNet-50 on the ImageNet dataset. We show that our method can be easily applied to other state-of-the-art "very deep" CNN models.

Yu-Xiao Guo, Xin Tong

We introduce a View-Volume convolutional neural network (VVNet) for inferring the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The VVNet concatenates a 2D view CNN and a 3D volume CNN with a differentiable projection layer. Given a single RGBD image, our method extracts the detailed geometric features from the input depth image with a 2D view CNN and then projects the features into a 3D volume according to the input depth map via a projection layer. After that, we learn the 3D context information of the scene with a 3D volume CNN for computing the result volumetric occupancy and semantic labels. With combined 2D and 3D representations, the VVNet efficiently reduces the computational cost, enables feature extraction from multi-channel high resolution inputs, and thus significantly improves the result accuracy. We validate our method and demonstrate its efficiency and effectiveness on both synthetic SUNCG and real NYU dataset.