OpenDLSS缺少关键输入导致性能高昂且缺乏训练数据
问题概述
OpenDLSS的实现未使用z‑buffer等关键控制输入，导致控制不完整；在1080p下单帧处理耗时约8ms，渲染预算过高；用户质疑在没有针对每个游戏的训练权重或专用模型的情况下，通用模型的实用性。
痛点标签
- 缺少z‑buffer输入导致控制不完整
- 在1080p下单帧处理耗时约8ms，渲染预算过高
- 缺乏针对每个游戏的训练权重，仅使用通用模型
待验证问题
- 是否可以在不提供z‑buffer的情况下实现相当的控制质量？
- 该实现的8ms延迟在实际游戏场景中是否可接受？
- 是否有计划提供针对不同游戏的专用训练模型或权重？
证据
原话 · @Anonymous
I'm rather surprised that it doesn't take the z-buffer as an input. I would have thought that would have provided useful information, it's one of the more useful forms of contolnet.
原话 · @Anonymous
Almost 8ms on 1080p resolution seems extremely expensive, does the original also eat into the rendering budget as much?
原话 · @Anonymous
How useful is this without weights?Isn't the mote that Nvidia has is they work with studios to generate the training data from the game, then they ship a model per game?Or is my knowledge outdated here and they're just using a single generalised model?
免责声明：本卡片由 AI 从社区讨论中提炼，属于「痛点证据」，是需求分析与验证的起点，不等同于「已验证的市场需求」。AI 存在分析局限，关键决策前请打开上方原始讨论人工复核。