Ziyu Zhang

Andrey Ignatov, Grigory Malivenko, Radu Timofte et al. · tencent-ai

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

Daniil Lisus, Johann Laconte, Keenan Burnett et al.

This paper presents a novel deep-learning-based approach to improve localizing radar measurements against lidar maps. This radar-lidar localization leverages the benefits of both sensors; radar is resilient against adverse weather, while lidar produces high-quality maps in clear conditions. However, owing in part to the unique artefacts present in radar measurements, radar-lidar localization has struggled to achieve comparable performance to lidar-lidar systems, preventing it from being viable for autonomous driving. This work builds on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information. To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library. The learned weights facilitate ICP by filtering out harmful radar points related to artefacts, noise, and even vehicles on the road. Combining an analytical approach with a learned weight reduces overall localization errors and improves convergence in radar-lidar ICP results run on real-world autonomous driving data. Our code base is publicly available to facilitate reproducibility and extensions.

Arvind V. Mahankali, David P. Woodruff, Ziyu Zhang

We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor networks. For tensor train decomposition, we give a bicriteria $(1 + \eps)$-approximation algorithm with a small bicriteria rank and $O(q \cdot \nnz(A))$ running time, up to lower order terms, which improves over the additive error algorithm of \cite{huber2017randomized}. We also show how to convert the algorithm of \cite{huber2017randomized} into a relative error algorithm, but their algorithm necessarily has a running time of $O(qr^2 \cdot \nnz(A)) + n \cdot \poly(qk/\eps)$ when converted to a $(1 + \eps)$-approximation algorithm with bicriteria rank $r$. To the best of our knowledge, our work is the first to achieve polynomial time relative error approximation for tensor train decomposition. Our key technique is a method for obtaining subspace embeddings with a number of rows polynomial in $q$ for a matrix which is the flattening of a tensor train of $q$ tensors. We extend our algorithm to tree tensor networks. In addition, we extend our algorithm to tensor networks with arbitrary graphs (which we refer to as general tensor networks), by using a result of \cite{ms08_simulating_quantum_tensor_contraction} and showing that a general tensor network of rank $k$ can be contracted to a binary tree network of rank $k^{O(°(G)\tw(G))}$, allowing us to reduce to the case of tree tensor networks. Finally, we give new fixed-parameter tractable algorithms for the tensor train, Tucker, and CP decompositions, which are simpler than those of \cite{swz19_tensor_low_rank} since they do not make use of polynomial system solvers. Our technique of Gaussian subspace embeddings with exactly $k$ rows (and thus exponentially small success probability) may be of independent interest.

Xinsheng Wang, Mingqi Jiang, Ziyang Ma et al.

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Chunyu Qiang, Xiaopeng Wang, Kang Yin et al.

Generative audio modeling has largely been fragmented into specialized tasks, text-to-speech (TTS), text-to-music (TTM), and text-to-audio (TTA), each operating under heterogeneous control paradigms. Unifying these modalities remains a fundamental challenge due to the intrinsic dissonance between structured semantic representations (speech/music) and unstructured acoustic textures (sound effects). In this paper, we introduce UniSonate, a unified flow-matching framework capable of synthesizing speech, music, and sound effects through a standardized, reference-free natural language instruction interface. To reconcile structural disparities, we propose a novel dynamic token injection mechanism that projects unstructured environmental sounds into a structured temporal latent space, enabling precise duration control within a phoneme-driven Multimodal Diffusion Transformer (MM-DiT). Coupled with a multi-stage curriculum learning strategy, this approach effectively mitigates cross-modal optimization conflicts. Extensive experiments demonstrate that UniSonate achieves state-of-the-art performance in instruction-based TTS (WER 1.47%) and TTM (SongEval Coherence 3.18), while maintaining competitive fidelity in TTA. Crucially, we observe positive transfer, where joint training on diverse audio data significantly enhances structural coherence and prosodic expressiveness compared to single-task baselines. Audio samples are available at https://qiangchunyu.github.io/UniSonate/.

Yuxuan Mu, Ziyu Zhang, Yi Shi et al.

Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters. Adversarial imitation learning has been a highly effective method for learning motion priors from reference motion data. However, adversarial priors, with few exceptions, need to be retrained for each new controller, thereby limiting their reusability and necessitating the retention of the reference motion data when training on downstream tasks. In this work, we present Score-Matching Motion Priors (SMP), which leverages pre-trained motion diffusion models and score distillation sampling (SDS) to create reusable task-agnostic motion priors. SMPs can be pre-trained on a motion dataset, independent of any control policy or task. Once trained, SMPs can be kept frozen and reused as general-purpose reward functions to train policies to produce naturalistic behaviors for downstream tasks. We show that a general motion prior trained on large-scale datasets can be repurposed into a variety of style-specific priors. Furthermore SMP can compose different styles to synthesize new styles not present in the original dataset. Our method produces high-quality motion comparable to state-of-the-art adversarial imitation learning methods through reusable and modular motion priors. We demonstrate the effectiveness of SMP across a diverse suite of control tasks with physically simulated humanoid characters. Video demo available at https://youtu.be/ravlZJteS20

Dewei Bai, Hongxiang Peng, Yunyun Zeng et al.

Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information. Incorporating delays in SNNs has been proven to be an effective mechanism for improving spike alignment in event-driven tasks. However, existing delay learning approaches predominantly assign static delays to individual synapses, resulting in a large number of delay parameters and limited adaptability to input-dependent activity dynamics. To this end, we propose a Congestion-Aware Dynamic Axonal Delay mechanism, decomposing the delay into a channel-wise static base delay for temporal structuring and a global, activity-conditioned shift that dynamically regulates the state update rate under varying spike intensities. The delay parameters are learned using differentiable linear interpolation and discretized at inference time, preserving the benefits of our dynamic delay while incurring only minimal additional cost. Experiments on speech benchmarks, including the Spiking Heidelberg Dataset, Spiking Speech Commands, and Google Speech Commands, demonstrate that introducing congestion-aware delays into synaptic signal transmission effectively improves accuracy on temporal tasks, notably achieving 93.75\% accuracy on SHD, 80.49\% accuracy on SSC, and 95.53\% on GSC-35, while reducing the parameter count by approximately 50\% compared to state-of-the-art delay-based methods with the same architecture.

Yuhang Dai, Ziyu Zhang, Shuai Wang et al.

The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce WenetSpeech-Chuan, a 10,000-hour, richly annotated corpus constructed using our novel Chuan-Pipeline, a complete data processing framework for dialectal speech. To facilitate rigorous evaluation and demonstrate the corpus's effectiveness, we also release high-quality ASR and TTS benchmarks, WenetSpeech-Chuan-Eval, with manually verified transcriptions. Experiments show that models trained on WenetSpeech-Chuan achieve state-of-the-art performance among open-source systems and demonstrate results comparable to commercial services. As the largest open-source corpus for Sichuanese dialects, WenetSpeech-Chuan not only lowers the barrier to research in dialectal speech processing but also plays a crucial role in promoting AI equity and mitigating bias in speech technologies. The corpus, benchmarks, models, and receipts are publicly available on our project page.

Wenjie Tian, Mingchen Shao, Bingshen Mu et al.

Audio-visual speech recognition (AVSR) is an extension of ASR that incorporates visual signals. Current AVSR approaches primarily focus on lip motion, largely overlooking rich context present in the video such as speaking scene and on-screen text. To tackle such CAVSR (AVSR including rich visual Context), we propose VASR designed to "see" and reason the visual context to improve speech recognition. Specifically, we construct an Audio-Visual Chain-of-Thought (AV-CoT) that explicitly enforces intermediate cross-modal grounding between acoustic signals and visual evidence. This evidence-driven reasoning mitigates the "single-modality dominance" problem, where models either over-rely on visual context or fail to utilize it. Besides, to address the data scarcity, we construct and release a corresponding data pipeline and test set. Experiments show that AV-CoT effectively mitigates the single-modality dominance, achieving state-of-the-art performance in CAVSR. The project is open-sourced.

Ziyu Zhang, Tianle Liu, Diantao Tu et al.

We present a fast 3DGS reconstruction pipeline designed to converge within one minute, developed for the SIGGRAPH Asia 3DGS Fast Reconstruction Challenge. The challenge consists of an initial round using SLAM-generated camera poses (with noisy trajectories) and a final round using COLMAP poses (highly accurate). To robustly handle these heterogeneous settings, we develop a two-stage solution. In the first round, we use reverse per-Gaussian parallel optimization and compact forward splatting based on Taming-GS and Speedy-splat, load-balanced tiling, an anchor-based Neural-Gaussian representation enabling rapid convergence with fewer learnable parameters, initialization from monocular depth and partially from feed-forward 3DGS models, and a global pose refinement module for noisy SLAM trajectories. In the final round, the accurate COLMAP poses change the optimization landscape; we disable pose refinement, revert from Neural-Gaussians back to standard 3DGS to eliminate MLP inference overhead, introduce multi-view consistency-guided Gaussian splitting inspired by Fast-GS, and introduce a depth estimator to supervise the rendered depth. Together, these techniques enable high-fidelity reconstruction under a strict one-minute budget. Our method achieved the top performance with a PSNR of 28.43 and ranked first in the competition.

Zeyu Cai, Jian Yu, Ziyu Zhang et al.

Spectral image reconstruction is an important task in snapshot compressed imaging. This paper aims to propose a new end-to-end framework with iterative capabilities similar to a deep unfolding network to improve reconstruction accuracy, independent of optimization conditions, and to reduce the number of parameters. A novel framework called the reversible-prior-based method is proposed. Inspired by the reversibility of the optical path, the reversible-prior-based framework projects the reconstructions back into the measurement space, and then the residuals between the projected data and the real measurements are fed into the network for iteration. The reconstruction subnet in the network then learns the mapping of the residuals to the true values to improve reconstruction accuracy. In addition, a novel spectral-spatial transformer is proposed to account for the global correlation of spectral data in both spatial and spectral dimensions while balancing network depth and computational complexity, in response to the shortcomings of existing transformer-based denoising modules that ignore spatial texture features or learn local spatial features at the expense of global spatial features. Extensive experiments show that our SST-ReversibleNet significantly outperforms state-of-the-art methods on simulated and real HSI datasets, while requiring lower computational and storage costs. https://github.com/caizeyu1992/SST

Dewei Bai, Hongxiang Peng, Yunyun Zeng et al.

Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-driven nature of spiking neural computation. To address this limitation, we propose Vision SmolMamba, an energy-efficient spiking state-space architecture that integrates spike-driven dynamics with linear-time selective recurrence. The key idea is a Spike-Guided Spatio-Temporal Token Pruner (SST-TP), which estimates token importance using both spike activation strength and first-spike latency. This mechanism progressively removes redundant tokens while preserving salient spatio-temporal information, enabling efficient scaling with token sparsity. Based on this mechanism, the proposed SmolMamba block incorporates spike events directly into bidirectional state-space recurrence, forming a spiking state-space vision backbone for efficient long-range modeling. Extensive experiments on both static and event-based benchmarks, including ImageNet-1K, CIFAR10/100, CIFAR10-DVS, and DVS128 Gesture, demonstrate that Vision SmolMamba consistently achieves superior accuracy-efficiency trade-offs. In particular, it reduces the estimated energy cost by at least 1.5x compared with prior spiking Transformer baselines and a Spiking Mamba variant while maintaining competitive or improved accuracy. These results demonstrate that combining spike-guided token sparsity with state-space modeling offers a scalable and energy-efficient paradigm for spiking vision systems.

Dake Guo, Jixun Yao, Xinfa Zhu et al.

This paper presents the NPU-HWC system submitted to the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC). Our system consists of two modules: a speech generator for Track 1 and a background audio generator for Track 2. In Track 1, we employ Single-Codec to tokenize the speech into discrete tokens and use a language-model-based approach to achieve zero-shot speaking style cloning. The Single-Codec effectively decouples timbre and speaking style at the token level, reducing the acoustic modeling burden on the autoregressive language model. Additionally, we use DSPGAN to upsample 16 kHz mel-spectrograms to high-fidelity 48 kHz waveforms. In Track 2, we propose a background audio generator based on large language models (LLMs). This system produces scene-appropriate accompaniment descriptions, synthesizes background audio with Tango 2, and integrates it with the speech generated by our Track 1 system. Our submission achieves the second place and the first place in Track 1 and Track 2 respectively.

Ziyu Zhang, Johann Laconte, Daniil Lisus et al.

This paper presents a novel method for assessing the resilience of the ICP algorithm via learning-based, worst-case attacks on lidar point clouds. For safety-critical applications such as autonomous navigation, ensuring the resilience of algorithms before deployments is crucial. The ICP algorithm is the standard for lidar-based localization, but its accuracy can be greatly affected by corrupted measurements from various sources, including occlusions, adverse weather, or mechanical sensor issues. Unfortunately, the complex and iterative nature of ICP makes assessing its resilience to corruption challenging. While there have been efforts to create challenging datasets and develop simulations to evaluate the resilience of ICP, our method focuses on finding the maximum possible ICP error that can arise from corrupted measurements at a location. We demonstrate that our perturbation-based adversarial attacks can be used pre-deployment to identify locations on a map where ICP is particularly vulnerable to corruptions in the measurements. With such information, autonomous robots can take safer paths when deployed, to mitigate against their measurements being corrupted. The proposed attack outperforms baselines more than 88% of the time across a wide range of scenarios.

Ziyu Zhang, Binbin Huang, Hanqing Jiang et al.

We propose Quadratic Gaussian Splatting (QGS), a novel representation that replaces static primitives with deformable quadric surfaces (e.g., ellipse, paraboloids) to capture intricate geometry. Unlike prior works that rely on Euclidean distance for primitive density modeling--a metric misaligned with surface geometry under deformation--QGS introduces geodesic distance-based density distributions. This innovation ensures that density weights adapt intrinsically to the primitive curvature, preserving consistency during shape changes (e.g., from planar disks to curved paraboloids). By solving geodesic distances in closed form on quadric surfaces, QGS enables surface-aware splatting, where a single primitive can represent complex curvature that previously required dozens of planar surfels, potentially reducing memory usage while maintaining efficient rendering via fast ray-quadric intersection. Experiments on DTU, Tanks and Temples, and MipNeRF360 datasets demonstrate state-of-the-art surface reconstruction, with QGS reducing geometric error (chamfer distance) by 33% over 2DGS and 27% over GOF on the DTU dataset. Crucially, QGS retains competitive appearance quality, bridging the gap between geometric precision and visual fidelity for applications like robotics and immersive reality.

Chunyu Qiang, Jun Wang, Xiaopeng Wang et al.

Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches either suffer from temporal misalignment due to cascaded generation or lack the capability to perform zero-shot voice cloning within a joint synthesis framework. In this work, we present MM-Sonate, a multimodal flow-matching framework that unifies controllable audio-video joint generation with zero-shot voice cloning capabilities. Unlike prior works that rely on coarse semantic descriptions, MM-Sonate utilizes a unified instruction-phoneme input to enforce strict linguistic and temporal alignment. To enable zero-shot voice cloning, we introduce a timbre injection mechanism that effectively decouples speaker identity from linguistic content. Furthermore, addressing the limitations of standard classifier-free guidance in multimodal settings, we propose a noise-based negative conditioning strategy that utilizes natural noise priors to significantly enhance acoustic fidelity. Empirical evaluations demonstrate that MM-Sonate establishes new state-of-the-art performance in joint generation benchmarks, significantly outperforming baselines in lip synchronization and speech intelligibility, while achieving voice cloning fidelity comparable to specialized Text-to-Speech systems.

Ziyu Zhang, Hanzhao Li, Jingbin Hu et al.

Controllable speech synthesis refers to the precise control of speaking style by manipulating specific prosodic and paralinguistic attributes, such as gender, volume, speech rate, pitch, and pitch fluctuation. With the integration of advanced generative models, particularly large language models (LLMs) and diffusion models, controllable text-to-speech (TTS) systems have increasingly transitioned from label-based control to natural language description-based control, which is typically implemented by predicting global style embeddings from textual prompts. However, this straightforward prediction overlooks the underlying distribution of the style embeddings, which may hinder the full potential of controllable TTS systems. In this study, we use t-SNE analysis to visualize and analyze the global style embedding distribution of various mainstream TTS systems, revealing a clear hierarchical clustering pattern: embeddings first cluster by timbre and subsequently subdivide into finer clusters based on style attributes. Based on this observation, we propose HiStyle, a two-stage style embedding predictor that hierarchically predicts style embeddings conditioned on textual prompts, and further incorporate contrastive learning to help align the text and audio embedding spaces. Additionally, we propose a style annotation strategy that leverages the complementary strengths of statistical methodologies and human auditory preferences to generate more accurate and perceptually consistent textual prompts for style control. Comprehensive experiments demonstrate that when applied to the base TTS model, HiStyle achieves significantly better style controllability than alternative style embedding predicting approaches while preserving high speech quality in terms of naturalness and intelligibility. Audio samples are available at https://anonymous.4open.science/w/HiStyle-2517/.

Ziyu Zhang, Sergey Bashkirov, Dun Yang et al.

Multi-objective optimization problems, which require the simultaneous optimization of multiple objectives, are prevalent across numerous applications. Existing multi-objective optimization methods often rely on manually-tuned aggregation functions to formulate a joint optimization objective. The performance of such hand-tuned methods is heavily dependent on careful weight selection, a time-consuming and laborious process. These limitations also arise in the setting of reinforcement-learning-based motion tracking methods for physically simulated characters, where intricately crafted reward functions are typically used to achieve high-fidelity results. Such solutions not only require domain expertise and significant manual tuning, but also limit the applicability of the resulting reward function across diverse skills. To bridge this gap, we present a novel adversarial multi-objective optimization technique that is broadly applicable to a range of multi-objective reinforcement-learning tasks, including motion tracking. Our proposed Adversarial Differential Discriminator (ADD) receives a single positive sample, yet is still effective at guiding the optimization process. We demonstrate that our technique can enable characters to closely replicate a variety of acrobatic and agile behaviors, achieving comparable quality to state-of-the-art motion-tracking methods, without relying on manually-designed reward functions. Code and results are available at https://add-moo.github.io/.

Ziyu Zhang, Ran Ding, Ying Zhu et al.

To enhance tourists' experiences and immersion, this paper proposes a narrative-driven travel planning framework called NarrativeGuide, which generates a geoculturally-grounded narrative script for travelers, offering a novel, role-playing experience for their journey. In the initial stage, NarrativeGuide constructs a knowledge graph for attractions within a city, then configures the worldview, character setting, and exposition based on the knowledge graph. Using this foundation, the knowledge graph is combined to generate an independent scene unit for each attraction. During the itinerary planning stage, NarrativeGuide models narrative-driven travel planning as an optimization problem, utilizing a genetic algorithm (GA) to refine the itinerary. Before evaluating the candidate itinerary, transition scripts are generated for each pair of adjacent attractions, which, along with the scene units, form a complete script. The weighted sum of script coherence, travel time, and attraction scores is then used as the fitness value to update the candidate solution set. In our experiments, we incorporated the TravelPlanner benchmark to systematically evaluate the planning capability of NarrativeGuide under complex constraints. In addition, we assessed its performance in terms of narrative coherence and cultural fit. The results show that NarrativeGuide demonstrates strong capabilities in both itinerary planning and script generation.

Yanyi Ding, Zhiyi Kuang, Yuxin Pei et al.

SARS-CoV-2 is an upper respiratory system RNA virus that has caused over 3 million deaths and infecting over 150 million worldwide as of May 2021. With thousands of strains sequenced to date, SARS-CoV-2 mutations pose significant challenges to scientists on keeping pace with vaccine development and public health measures. Therefore, an efficient method of identifying the divergence of lab samples from patients would greatly aid the documentation of SARS-CoV-2 genomics. In this study, we propose a neural network model that leverages recurrent and convolutional units to directly take in amino acid sequences of spike proteins and classify corresponding clades. We also compared our model's performance with Bidirectional Encoder Representations from Transformers (BERT) pre-trained on protein database. Our approach has the potential of providing a more computationally efficient alternative to current homology based intra-species differentiation.

Andrey Ignatov, Grigory Malivenko, David Plowman et al.

Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper.

Yi Yu, Feipeng Da, Ziyu Zhang

3D face recognition has shown its potential in many application scenarios. Among numerous 3D face recognition methods, deep-learning-based methods have developed vigorously in recent years. In this paper, an end-to-end deep learning network entitled Sur3dNet-Face for point-cloud-based 3D face recognition is proposed. The network uses PointNet as the backbone, which is a successful point cloud classification solution but does not work properly in face recognition. Supplemented with modifications in network architecture and a few-data guided learning framework based on Gaussian process morphable model, the backbone is successfully modified for 3D face recognition. Different from existing methods training with a large amount of data in multiple datasets, our method uses Spring2003 subset of FRGC v2.0 for training which contains only 943 facial scans, and the network is well trained with the guidance of such a small amount of real data. Without fine-tuning on the test set, the Rank-1 Recognition Rate (RR1) is achieved as follows: 98.85% on FRGC v2.0 dataset and 99.33% on Bosphorus dataset, which proves the effectiveness and the potentiality of our method.

Ziyu Zhang, Feipeng Da, Yi Yu

Point clouds-based Networks have achieved great attention in 3D object classification, segmentation and indoor scene semantic parsing. In terms of face recognition, 3D face recognition method which directly consume point clouds as input is still under study. Two main factors account for this: One is how to get discriminative face representations from 3D point clouds using deep network; the other is the lack of large 3D training dataset. To address these problems, a data-free 3D face recognition method is proposed only using synthesized unreal data from statistical 3D Morphable Model to train a deep point cloud network. To ease the inconsistent distribution between model data and real faces, different point sampling methods are used in train and test phase. In this paper, we propose a curvature-aware point sampling(CPS) strategy replacing the original furthest point sampling(FPS) to hierarchically down-sample feature-sensitive points which are crucial to pass and aggregate features deeply. A PointNet++ like Network is used to extract face features directly from point clouds. The experimental results show that the network trained on generated data generalizes well for real 3D faces. Fine tuning on a small part of FRGCv2.0 and Bosphorus, which include real faces in different poses and expressions, further improves recognition accuracy.

Ishan Deshpande, Ziyu Zhang, Alexander Schwing

Generative Adversarial Nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often not stable. While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddle-point formulation. By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. Further, unlike the traditional GAN loss, the loss formulated in our method is a good measure of the actual distance between the distributions and, for the first time for GAN training, we are able to show estimates for the same.

Unnat Jain, Ziyu Zhang, Alexander Schwing

Generating diverse questions for given images is an important task for computational education, entertainment and AI assistants. Different from many conventional prediction techniques is the need for algorithms to generate a diverse set of plausible questions, which we refer to as "creativity". In this paper we propose a creative algorithm for visual question generation which combines the advantages of variational autoencoders with long short-term memory networks. We demonstrate that our framework is able to generate a large set of varying questions given a single input image.

Ziyu Zhang, Sanja Fidler, Raquel Urtasun

Our aim is to provide a pixel-wise instance-level labeling of a monocular image in the context of autonomous driving. We build on recent work [Zhang et al., ICCV15] that trained a convolutional neural net to predict instance labeling in local image patches, extracted exhaustively in a stride from an image. A simple Markov random field model using several heuristics was then proposed in [Zhang et al., ICCV15] to derive a globally consistent instance labeling of the image. In this paper, we formulate the global labeling problem with a novel densely connected Markov random field and show how to encode various intuitive potentials in a way that is amenable to efficient mean field inference [Krähenbühl et al., NIPS11]. Our potentials encode the compatibility between the global labeling and the patch-level predictions, contrast-sensitive smoothness as well as the fact that separate regions form different instances. Our experiments on the challenging KITTI benchmark [Geiger et al., CVPR12] demonstrate that our method achieves a significant performance boost over the baseline [Zhang et al., ICCV15].

Ziyu Zhang, Alexander G. Schwing, Sanja Fidler et al.

In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where the instance ID encodes the depth ordering within image patches. To provide a coherent single explanation of an image we develop a Markov random field which takes as input the predictions of convolutional neural nets applied at overlapping patches of different resolutions, as well as the output of a connected component algorithm. It aims to predict accurate instance-level segmentation and depth ordering. We demonstrate the effectiveness of our approach on the challenging KITTI benchmark and show good performance on both tasks.