Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering. However, 3D-aware synthesis of face dynamics hasn't received much attention. Here, we study how to explicitly control generative model synthesis of face dynamics exhibiting non-rigid motion (e.g., facial expression change), while simultaneously ensuring 3D-awareness. For this we propose a Controllable Radiance Field (CoRF): 1) Motion control is achieved by embedding motion features within the layered latent motion space of a style-based generator; 2) To ensure consistency of background, motion features and subject-specific attributes such as lighting, texture, shapes, albedo, and identity, a face parsing net, a head regressor and an identity encoder are incorporated. On head image/video data we show that CoRFs are 3D-aware while enabling editing of identity, viewing directions, and motion.
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations. Nonetheless, for downstream inference, CLIP-like models suffer from either 1) degraded accuracy and robustness in the case of inaccurate text descriptions during retrieval-based inference (the challenge for zero-shot protocol); or 2) breaking the well-established vision-language alignment (the challenge for linear probing). To address them, we propose Decomposed Feature Prompting (DeFo). DeFo leverages a flexible number of learnable embeddings as textual input while maintaining the vision-language dual-model architecture, which enables the model to learn decomposed visual features with the help of feature-level textual prompts. We further use an additional linear layer to perform classification, allowing a scalable size of language inputs. Our empirical study shows DeFo's significance in improving the vision-language models. For example, DeFo obtains 73.2% test accuracy on ImageNet with a ResNet-50 backbone without tuning any pretrained weights of both the vision and language encoder, outperforming zero-shot CLIP by a large margin of 15.0%, and outperforming state-of-the-art vision-language prompt tuning method by 7.6%.
Single-view RGB-D human reconstruction with implicit functions is often formulated as per-point classification. Specifically, a set of 3D locations within the view-frustum of the camera are first projected independently onto the image and a corresponding feature is subsequently extracted for each 3D location. The feature of each 3D location is then used to classify independently whether the corresponding 3D point is inside or outside the observed object. This procedure leads to sub-optimal results because correlations between predictions for neighboring locations are only taken into account implicitly via the extracted features. For more accurate results we propose the occupancy planes (OPlanes) representation, which enables to formulate single-view RGB-D human reconstruction as occupancy prediction on planes which slice through the camera's view frustum. Such a representation provides more flexibility than voxel grids and enables to better leverage correlations than per-point classification. On the challenging S3D data we observe a simple classifier based on the OPlanes representation to yield compelling results, especially in difficult situations with partial occlusions due to other objects and partial visibility, which haven't been addressed by prior work.
While recovery of geometry from image and video data has received a lot of attention in computer vision, methods to capture the texture for a given geometry are less mature. Specifically, classical methods for texture generation often assume clean geometry and reasonably well-aligned image data. While very recent methods, e.g., adversarial texture optimization, better handle lower-quality data obtained from hand-held devices, we find them to still struggle frequently. To improve robustness, particularly of recent adversarial texture optimization, we develop an explicit initialization and an alignment procedure. It deals with complex geometry due to a robust mapping of the geometry to the texture map and a hard-assignment-based initialization. It deals with misalignment of geometry and images by integrating fast image-alignment into the texture refinement optimization. We demonstrate efficacy of our texture generation on a dataset of 11 scenes with a total of 2807 frames, observing 7.8% and 11.1% relative improvements regarding perceptual and sharpness measurements.
What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator. We refer to the generated output as a 'generative multiplane image' (GMPI) and emphasize that its renderings are not only high-quality but also guaranteed to be view-consistent, which makes GMPIs different from many prior works. Importantly, the number of alpha maps can be dynamically adjusted and can differ between training and inference, alleviating memory concerns and enabling fast training of GMPIs in less than half a day at a resolution of $1024^2$. Our findings are consistent across three challenging and common high-resolution datasets, including FFHQ, AFHQv2, and MetFaces.
We present XMem, a video object segmentation architecture for long videos with unified feature memory stores inspired by the Atkinson-Shiffrin memory model. Prior work on video object segmentation typically only uses one type of feature memory. For videos longer than a minute, a single feature memory model tightly links memory consumption and accuracy. In contrast, following the Atkinson-Shiffrin model, we develop an architecture that incorporates multiple independent yet deeply-connected feature memory stores: a rapidly updated sensory memory, a high-resolution working memory, and a compact thus sustained long-term memory. Crucially, we develop a memory potentiation algorithm that routinely consolidates actively used working memory elements into the long-term memory, which avoids memory explosion and minimizes performance decay for long-term prediction. Combined with a new memory reading mechanism, XMem greatly exceeds state-of-the-art performance on long-video datasets while being on par with state-of-the-art methods (that do not work on long videos) on short-video datasets. Code is available at https://hkchengrex.github.io/XMem
We introduce an approach for selecting objects in neural volumetric 3D representations, such as multi-plane images (MPI) and neural radiance fields (NeRF). Our approach takes a set of foreground and background 2D user scribbles in one view and automatically estimates a 3D segmentation of the desired object, which can be rendered into novel views. To achieve this result, we propose a novel voxel feature embedding that incorporates the neural volumetric 3D representation and multi-view image features from all input views. To evaluate our approach, we introduce a new dataset of human-provided segmentation masks for depicted objects in real-world multi-view scene captures. We show that our approach out-performs strong baselines, including 2D segmentation and 3D segmentation approaches adapted to our task.
To solve difficult tasks, humans ask questions to acquire knowledge from external sources. In contrast, classical reinforcement learning agents lack such an ability and often resort to exploratory behavior. This is exacerbated as few present-day environments support querying for knowledge. In order to study how agents can be taught to query external knowledge via language, we first introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. In addition to physical interactions, an agent can query an external knowledge source specialized for these environments to gather information. Second, we propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge that helps solve the tasks. AFK leverages a non-parametric memory, a pointer mechanism and an episodic exploration bonus to tackle (1) a large query language space, (2) irrelevant information, (3) delayed reward for making meaningful queries. Extensive experiments demonstrate that the AFK agent outperforms recent baselines on the challenging Q-BabyAI and Q-TextWorld environments.
Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vision tasks: (a) which optimization problem within a layer is useful?; (b) how to ensure that computation within a layer remains efficient? To study question (a), in this work, we propose total variation (TV) minimization as a layer for computer vision. Motivated by the success of total variation in image processing, we hypothesize that TV as a layer provides useful inductive bias for deep-nets too. We study this hypothesis on five computer vision tasks: image classification, weakly supervised object localization, edge-preserving smoothing, edge detection, and image denoising, improving over existing baselines. To achieve these results we had to address question (b): we developed a GPU-based projected-Newton method which is $37\times$ faster than existing solutions.
Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation equivariance. However, incorporating these inductive biases requires knowledge about the equivariance properties of the data, which may not be available, e.g., when encountering a new domain. To address this, we study how to discover interpretable equivariances from data. Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes. We propose to use the partition distance to empirically quantify the accuracy of the recovered equivariance. Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme. Empirically, we show that the approach recovers known equivariances, such as permutations and shifts, on sum of numbers and spatially-invariant data.